BibTeX records: Jaime Lorenzo-Trueba

download as .bib file

@article{DBLP:journals/corr/abs-2402-03407,
  author       = {{\'{A}}lvaro Mart{\'{\i}}n{-}Cortinas and
                  Daniel S{\'{a}}ez{-}Trigueros and
                  Iv{\'{a}}n Vall{\'{e}}s{-}P{\'{e}}rez and
                  Biel Tura Vecino and
                  Piotr Bilinski and
                  Mateusz Lajszczak and
                  Grzegorz Beringer and
                  Roberto Barra{-}Chicote and
                  Jaime Lorenzo{-}Trueba},
  title        = {Enhancing the Stability of LLM-based Speech Generation Systems through
                  Self-Supervised Representations},
  journal      = {CoRR},
  volume       = {abs/2402.03407},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2402.03407},
  doi          = {10.48550/ARXIV.2402.03407},
  eprinttype    = {arXiv},
  eprint       = {2402.03407},
  timestamp    = {Thu, 15 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-03407.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-16643,
  author       = {Manuel Sam Ribeiro and
                  Giulia Comini and
                  Jaime Lorenzo{-}Trueba},
  title        = {Improving grapheme-to-phoneme conversion by learning pronunciations
                  from speech recordings},
  journal      = {CoRR},
  volume       = {abs/2307.16643},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2307.16643},
  doi          = {10.48550/ARXIV.2307.16643},
  eprinttype    = {arXiv},
  eprint       = {2307.16643},
  timestamp    = {Tue, 01 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2307-16643.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-16679,
  author       = {Guangyan Zhang and
                  Thomas Merritt and
                  Manuel Sam Ribeiro and
                  Biel Tura Vecino and
                  Kayoko Yanagisawa and
                  Kamil Pokora and
                  Abdelhamid Ezzerg and
                  Sebastian Cygert and
                  Ammar Abbas and
                  Piotr Bilinski and
                  Roberto Barra{-}Chicote and
                  Daniel Korzekwa and
                  Jaime Lorenzo{-}Trueba},
  title        = {Comparing normalizing flows and diffusion models for prosody and acoustic
                  modelling in text-to-speech},
  journal      = {CoRR},
  volume       = {abs/2307.16679},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2307.16679},
  doi          = {10.48550/ARXIV.2307.16679},
  eprinttype    = {arXiv},
  eprint       = {2307.16679},
  timestamp    = {Tue, 01 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2307-16679.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-16709,
  author       = {Giulia Comini and
                  Manuel Sam Ribeiro and
                  Fan Yang and
                  Heereen Shim and
                  Jaime Lorenzo{-}Trueba},
  title        = {Multilingual context-based pronunciation learning for Text-to-Speech},
  journal      = {CoRR},
  volume       = {abs/2307.16709},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2307.16709},
  doi          = {10.48550/ARXIV.2307.16709},
  eprinttype    = {arXiv},
  eprint       = {2307.16709},
  timestamp    = {Wed, 02 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2307-16709.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/KorzekwaLDK22,
  author       = {Daniel Korzekwa and
                  Jaime Lorenzo{-}Trueba and
                  Thomas Drugman and
                  Bozena Kostek},
  title        = {Computer-assisted pronunciation training - Speech synthesis is almost
                  all you need},
  journal      = {Speech Commun.},
  volume       = {142},
  pages        = {22--33},
  year         = {2022},
  url          = {https://doi.org/10.1016/j.specom.2022.06.003},
  doi          = {10.1016/J.SPECOM.2022.06.003},
  timestamp    = {Thu, 25 Aug 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/speech/KorzekwaLDK22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/RibeiroRCHGL22,
  author       = {Manuel Sam Ribeiro and
                  Julian Roth and
                  Giulia Comini and
                  Goeric Huybrechts and
                  Adam Gabrys and
                  Jaime Lorenzo{-}Trueba},
  title        = {Cross-Speaker Style Transfer for Text-to-Speech Using Data Augmentation},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  pages        = {6797--6801},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/ICASSP43922.2022.9746179},
  doi          = {10.1109/ICASSP43922.2022.9746179},
  timestamp    = {Tue, 07 Jun 2022 17:34:47 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/RibeiroRCHGL22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GabrysHRCRCBPL22,
  author       = {Adam Gabrys and
                  Goeric Huybrechts and
                  Manuel Sam Ribeiro and
                  Chung{-}Ming Chien and
                  Julian Roth and
                  Giulia Comini and
                  Roberto Barra{-}Chicote and
                  Bartek Perz and
                  Jaime Lorenzo{-}Trueba},
  title        = {Voice Filter: Few-Shot Text-to-Speech Speaker Adaptation Using Voice
                  Conversion as a Post-Processing Module},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  pages        = {7902--7906},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/ICASSP43922.2022.9747239},
  doi          = {10.1109/ICASSP43922.2022.9747239},
  timestamp    = {Tue, 07 Jun 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/GabrysHRCRCBPL22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CominiHRGL22,
  author       = {Giulia Comini and
                  Goeric Huybrechts and
                  Manuel Sam Ribeiro and
                  Adam Gabrys and
                  Jaime Lorenzo{-}Trueba},
  editor       = {Hanseok Ko and
                  John H. L. Hansen},
  title        = {Low-data? No problem: low-resource, language-agnostic conversational
                  text-to-speech via F0-conditioned data augmentation},
  booktitle    = {Interspeech 2022, 23rd Annual Conference of the International Speech
                  Communication Association, Incheon, Korea, 18-22 September 2022},
  pages        = {1946--1950},
  publisher    = {{ISCA}},
  year         = {2022},
  url          = {https://doi.org/10.21437/Interspeech.2022-10338},
  doi          = {10.21437/INTERSPEECH.2022-10338},
  timestamp    = {Wed, 21 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/CominiHRGL22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-05083,
  author       = {Manuel Sam Ribeiro and
                  Julian Roth and
                  Giulia Comini and
                  Goeric Huybrechts and
                  Adam Gabrys and
                  Jaime Lorenzo{-}Trueba},
  title        = {Cross-speaker style transfer for text-to-speech using data augmentation},
  journal      = {CoRR},
  volume       = {abs/2202.05083},
  year         = {2022},
  url          = {https://arxiv.org/abs/2202.05083},
  eprinttype    = {arXiv},
  eprint       = {2202.05083},
  timestamp    = {Tue, 01 Mar 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2202-05083.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-08164,
  author       = {Adam Gabrys and
                  Goeric Huybrechts and
                  Manuel Sam Ribeiro and
                  Chung{-}Ming Chien and
                  Julian Roth and
                  Giulia Comini and
                  Roberto Barra{-}Chicote and
                  Bartek Perz and
                  Jaime Lorenzo{-}Trueba},
  title        = {Voice Filter: Few-shot text-to-speech speaker adaptation using voice
                  conversion as a post-processing module},
  journal      = {CoRR},
  volume       = {abs/2202.08164},
  year         = {2022},
  url          = {https://arxiv.org/abs/2202.08164},
  eprinttype    = {arXiv},
  eprint       = {2202.08164},
  timestamp    = {Tue, 01 Mar 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2202-08164.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-00774,
  author       = {Daniel Korzekwa and
                  Jaime Lorenzo{-}Trueba and
                  Thomas Drugman and
                  Bozena Kostek},
  title        = {Computer-assisted Pronunciation Training - Speech synthesis is almost
                  all you need},
  journal      = {CoRR},
  volume       = {abs/2207.00774},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2207.00774},
  doi          = {10.48550/ARXIV.2207.00774},
  eprinttype    = {arXiv},
  eprint       = {2207.00774},
  timestamp    = {Wed, 06 Jul 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2207-00774.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-14607,
  author       = {Giulia Comini and
                  Goeric Huybrechts and
                  Manuel Sam Ribeiro and
                  Adam Gabrys and
                  Jaime Lorenzo{-}Trueba},
  title        = {Low-data? No problem: low-resource, language-agnostic conversational
                  text-to-speech via F0-conditioned data augmentation},
  journal      = {CoRR},
  volume       = {abs/2207.14607},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2207.14607},
  doi          = {10.48550/ARXIV.2207.14607},
  eprinttype    = {arXiv},
  eprint       = {2207.14607},
  timestamp    = {Tue, 02 Aug 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2207-14607.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HodariMKLMJAKD21,
  author       = {Zack Hodari and
                  Alexis Moinet and
                  Sri Karlapati and
                  Jaime Lorenzo{-}Trueba and
                  Thomas Merritt and
                  Arnaud Joly and
                  Ammar Abbas and
                  Penny Karanasou and
                  Thomas Drugman},
  title        = {Camp: {A} Two-Stage Approach to Modelling Prosody in Context},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  pages        = {6578--6582},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/ICASSP39728.2021.9414413},
  doi          = {10.1109/ICASSP39728.2021.9414413},
  timestamp    = {Fri, 09 Jul 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/HodariMKLMJAKD21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HuybrechtsMCPSL21,
  author       = {Goeric Huybrechts and
                  Thomas Merritt and
                  Giulia Comini and
                  Bartek Perz and
                  Raahil Shah and
                  Jaime Lorenzo{-}Trueba},
  title        = {Low-Resource Expressive Text-To-Speech Using Data Augmentation},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  pages        = {6593--6597},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/ICASSP39728.2021.9413466},
  doi          = {10.1109/ICASSP39728.2021.9413466},
  timestamp    = {Fri, 09 Jul 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/HuybrechtsMCPSL21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KorzekwaLZCDK21,
  author       = {Daniel Korzekwa and
                  Jaime Lorenzo{-}Trueba and
                  Szymon Zaporowski and
                  Shira Calamaro and
                  Thomas Drugman and
                  Bozena Kostek},
  title        = {Mispronunciation Detection in Non-Native {(L2)} English with Uncertainty
                  Modeling},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
  pages        = {7738--7742},
  publisher    = {{IEEE}},
  year         = {2021},
  url          = {https://doi.org/10.1109/ICASSP39728.2021.9413953},
  doi          = {10.1109/ICASSP39728.2021.9413953},
  timestamp    = {Fri, 09 Jul 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/KorzekwaLZCDK21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KaranasouKMJASL21,
  author       = {Penny Karanasou and
                  Sri Karlapati and
                  Alexis Moinet and
                  Arnaud Joly and
                  Ammar Abbas and
                  Simon Slangen and
                  Jaime Lorenzo{-}Trueba and
                  Thomas Drugman},
  editor       = {Hynek Hermansky and
                  Honza Cernock{\'{y}} and
                  Luk{\'{a}}s Burget and
                  Lori Lamel and
                  Odette Scharenborg and
                  Petr Motl{\'{\i}}cek},
  title        = {A Learned Conditional Prior for the {VAE} Acoustic Space of a {TTS}
                  System},
  booktitle    = {Interspeech 2021, 22nd Annual Conference of the International Speech
                  Communication Association, Brno, Czechia, 30 August - 3 September
                  2021},
  pages        = {3620--3624},
  publisher    = {{ISCA}},
  year         = {2021},
  url          = {https://doi.org/10.21437/Interspeech.2021-528},
  doi          = {10.21437/INTERSPEECH.2021-528},
  timestamp    = {Wed, 21 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/KaranasouKMJASL21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KorzekwaBZBLSDD21,
  author       = {Daniel Korzekwa and
                  Roberto Barra{-}Chicote and
                  Szymon Zaporowski and
                  Grzegorz Beringer and
                  Jaime Lorenzo{-}Trueba and
                  Alicja Serafinowicz and
                  Jasha Droppo and
                  Thomas Drugman and
                  Bozena Kostek},
  editor       = {Hynek Hermansky and
                  Honza Cernock{\'{y}} and
                  Luk{\'{a}}s Burget and
                  Lori Lamel and
                  Odette Scharenborg and
                  Petr Motl{\'{\i}}cek},
  title        = {Detection of Lexical Stress Errors in Non-Native {(L2)} English with
                  Data Augmentation and Attention},
  booktitle    = {Interspeech 2021, 22nd Annual Conference of the International Speech
                  Communication Association, Brno, Czechia, 30 August - 3 September
                  2021},
  pages        = {3915--3919},
  publisher    = {{ISCA}},
  year         = {2021},
  url          = {https://doi.org/10.21437/Interspeech.2021-86},
  doi          = {10.21437/INTERSPEECH.2021-86},
  timestamp    = {Wed, 21 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/KorzekwaBZBLSDD21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KorzekwaLDCK21,
  author       = {Daniel Korzekwa and
                  Jaime Lorenzo{-}Trueba and
                  Thomas Drugman and
                  Shira Calamaro and
                  Bozena Kostek},
  editor       = {Hynek Hermansky and
                  Honza Cernock{\'{y}} and
                  Luk{\'{a}}s Burget and
                  Lori Lamel and
                  Odette Scharenborg and
                  Petr Motl{\'{\i}}cek},
  title        = {Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native
                  English Speech},
  booktitle    = {Interspeech 2021, 22nd Annual Conference of the International Speech
                  Communication Association, Brno, Czechia, 30 August - 3 September
                  2021},
  pages        = {4408--4412},
  publisher    = {{ISCA}},
  year         = {2021},
  url          = {https://doi.org/10.21437/Interspeech.2021-38},
  doi          = {10.21437/INTERSPEECH.2021-38},
  timestamp    = {Wed, 21 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/KorzekwaLDCK21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/TyagiBLL21,
  author       = {Shubhi Tyagi and
                  Antonio Bonafonte and
                  Jaime Lorenzo{-}Trueba and
                  Javier Latorre},
  editor       = {Young{-}bum Kim and
                  Yunyao Li and
                  Owen Rambow},
  title        = {Proteno: Text Normalization with Limited Data for Fast Deployment
                  in Text to Speech Systems},
  booktitle    = {Proceedings of the 2021 Conference of the North American Chapter of
                  the Association for Computational Linguistics: Human Language Technologies:
                  Industry Papers, {NAACL-HLT} 2021, Online, June 6-11, 2021},
  pages        = {72--79},
  publisher    = {Association for Computational Linguistics},
  year         = {2021},
  url          = {https://doi.org/10.18653/v1/2021.naacl-industry.10},
  doi          = {10.18653/V1/2021.NAACL-INDUSTRY.10},
  timestamp    = {Wed, 15 Nov 2023 13:49:17 +0100},
  biburl       = {https://dblp.org/rec/conf/naacl/TyagiBLL21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-05695,
  author       = {Bastian Schnell and
                  Goeric Huybrechts and
                  Bartek Perz and
                  Thomas Drugman and
                  Jaime Lorenzo{-}Trueba},
  title        = {EmoCat: Language-agnostic Emotional Voice Conversion},
  journal      = {CoRR},
  volume       = {abs/2101.05695},
  year         = {2021},
  url          = {https://arxiv.org/abs/2101.05695},
  eprinttype    = {arXiv},
  eprint       = {2101.05695},
  timestamp    = {Tue, 26 Jan 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2101-05695.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-06396,
  author       = {Daniel Korzekwa and
                  Jaime Lorenzo{-}Trueba and
                  Szymon Zaporowski and
                  Shira Calamaro and
                  Thomas Drugman and
                  Bozena Kostek},
  title        = {Mispronunciation Detection in Non-native {(L2)} English with Uncertainty
                  Modeling},
  journal      = {CoRR},
  volume       = {abs/2101.06396},
  year         = {2021},
  url          = {https://arxiv.org/abs/2101.06396},
  eprinttype    = {arXiv},
  eprint       = {2101.06396},
  timestamp    = {Tue, 26 Jan 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2101-06396.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-07777,
  author       = {Shubhi Tyagi and
                  Antonio Bonafonte and
                  Jaime Lorenzo{-}Trueba and
                  Javier Latorre},
  title        = {Proteno: Text Normalization with Limited Data for Fast Deployment
                  in Text to Speech Systems},
  journal      = {CoRR},
  volume       = {abs/2104.07777},
  year         = {2021},
  url          = {https://arxiv.org/abs/2104.07777},
  eprinttype    = {arXiv},
  eprint       = {2104.07777},
  timestamp    = {Mon, 19 Apr 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2104-07777.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-03494,
  author       = {Daniel Korzekwa and
                  Jaime Lorenzo{-}Trueba and
                  Thomas Drugman and
                  Shira Calamaro and
                  Bozena Kostek},
  title        = {Weakly-supervised word-level pronunciation error detection in non-native
                  English speech},
  journal      = {CoRR},
  volume       = {abs/2106.03494},
  year         = {2021},
  url          = {https://arxiv.org/abs/2106.03494},
  eprinttype    = {arXiv},
  eprint       = {2106.03494},
  timestamp    = {Fri, 11 Jun 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-03494.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-08873,
  author       = {Alejandro Mottini and
                  Jaime Lorenzo{-}Trueba and
                  Sri Vishnu Kumar Karlapati and
                  Thomas Drugman},
  title        = {Voicy: Zero-Shot Non-Parallel Voice Conversion in Noisy Reverberant
                  Environments},
  journal      = {CoRR},
  volume       = {abs/2106.08873},
  year         = {2021},
  url          = {https://arxiv.org/abs/2106.08873},
  eprinttype    = {arXiv},
  eprint       = {2106.08873},
  timestamp    = {Tue, 29 Jun 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-08873.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-10229,
  author       = {Penny Karanasou and
                  Sri Karlapati and
                  Alexis Moinet and
                  Arnaud Joly and
                  Ammar Abbas and
                  Simon Slangen and
                  Jaime Lorenzo{-}Trueba and
                  Thomas Drugman},
  title        = {A learned conditional prior for the {VAE} acoustic space of a {TTS}
                  system},
  journal      = {CoRR},
  volume       = {abs/2106.10229},
  year         = {2021},
  url          = {https://arxiv.org/abs/2106.10229},
  eprinttype    = {arXiv},
  eprint       = {2106.10229},
  timestamp    = {Thu, 01 Jul 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-10229.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-06270,
  author       = {Abdelhamid Ezzerg and
                  Adam Gabrys and
                  Bartosz Putrycz and
                  Daniel Korzekwa and
                  Daniel Saez{-}Trigueros and
                  David McHardy and
                  Kamil Pokora and
                  Jakub Lachowicz and
                  Jaime Lorenzo{-}Trueba and
                  Viacheslav Klimkov},
  title        = {Enhancing audio quality for expressive Neural Text-to-Speech},
  journal      = {CoRR},
  volume       = {abs/2108.06270},
  year         = {2021},
  url          = {https://arxiv.org/abs/2108.06270},
  eprinttype    = {arXiv},
  eprint       = {2108.06270},
  timestamp    = {Fri, 20 Aug 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2108-06270.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/CotescuDHLM20,
  author       = {Marius Cotescu and
                  Thomas Drugman and
                  Goeric Huybrechts and
                  Jaime Lorenzo{-}Trueba and
                  Alexis Moinet},
  title        = {Voice Conversion for Whispered Speech Synthesis},
  journal      = {{IEEE} Signal Process. Lett.},
  volume       = {27},
  pages        = {186--190},
  year         = {2020},
  url          = {https://doi.org/10.1109/LSP.2019.2961213},
  doi          = {10.1109/LSP.2019.2961213},
  timestamp    = {Tue, 03 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/spl/CotescuDHLM20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/AggarwalCPLB20,
  author       = {Vatsal Aggarwal and
                  Marius Cotescu and
                  Nishant Prateek and
                  Jaime Lorenzo{-}Trueba and
                  Roberto Barra{-}Chicote},
  title        = {Using Vaes and Normalizing Flows for One-Shot Text-To-Speech Synthesis
                  of Expressive Speech},
  booktitle    = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  pages        = {6179--6183},
  publisher    = {{IEEE}},
  year         = {2020},
  url          = {https://doi.org/10.1109/ICASSP40776.2020.9053678},
  doi          = {10.1109/ICASSP40776.2020.9053678},
  timestamp    = {Thu, 23 Jul 2020 16:19:28 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/AggarwalCPLB20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TyagiNRDL20,
  author       = {Shubhi Tyagi and
                  Marco Nicolis and
                  Jonas Rohnke and
                  Thomas Drugman and
                  Jaime Lorenzo{-}Trueba},
  editor       = {Helen Meng and
                  Bo Xu and
                  Thomas Fang Zheng},
  title        = {Dynamic Prosody Generation for Speech Synthesis Using Linguistics-Driven
                  Acoustic Embedding Selection},
  booktitle    = {Interspeech 2020, 21st Annual Conference of the International Speech
                  Communication Association, Virtual Event, Shanghai, China, 25-29 October
                  2020},
  pages        = {4407--4411},
  publisher    = {{ISCA}},
  year         = {2020},
  url          = {https://doi.org/10.21437/Interspeech.2020-1411},
  doi          = {10.21437/INTERSPEECH.2020-1411},
  timestamp    = {Fri, 29 Jan 2021 17:40:16 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/TyagiNRDL20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-05707,
  author       = {Goeric Huybrechts and
                  Thomas Merritt and
                  Giulia Comini and
                  Bartek Perz and
                  Raahil Shah and
                  Jaime Lorenzo{-}Trueba},
  title        = {Low-resource expressive text-to-speech using data augmentation},
  journal      = {CoRR},
  volume       = {abs/2011.05707},
  year         = {2020},
  url          = {https://arxiv.org/abs/2011.05707},
  eprinttype    = {arXiv},
  eprint       = {2011.05707},
  timestamp    = {Mon, 01 Mar 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2011-05707.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-09703,
  author       = {Jonas Rohnke and
                  Thomas Merritt and
                  Jaime Lorenzo{-}Trueba and
                  Adam Gabrys and
                  Vatsal Aggarwal and
                  Alexis Moinet and
                  Roberto Barra{-}Chicote},
  title        = {Parallel WaveNet conditioned on {VAE} latent vectors},
  journal      = {CoRR},
  volume       = {abs/2012.09703},
  year         = {2020},
  url          = {https://arxiv.org/abs/2012.09703},
  eprinttype    = {arXiv},
  eprint       = {2012.09703},
  timestamp    = {Mon, 01 Mar 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2012-09703.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-14788,
  author       = {Daniel Korzekwa and
                  Roberto Barra{-}Chicote and
                  Szymon Zaporowski and
                  Grzegorz Beringer and
                  Jaime Lorenzo{-}Trueba and
                  Alicja Serafinowicz and
                  Jasha Droppo and
                  Thomas Drugman and
                  Bozena Kostek},
  title        = {Detection of Lexical Stress Errors in Non-native {(L2)} English with
                  Data Augmentation and Attention},
  journal      = {CoRR},
  volume       = {abs/2012.14788},
  year         = {2020},
  url          = {https://arxiv.org/abs/2012.14788},
  eprinttype    = {arXiv},
  eprint       = {2012.14788},
  timestamp    = {Fri, 08 Jan 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2012-14788.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LatorreLLMDRK19,
  author       = {Javier Latorre and
                  Jakub Lachowicz and
                  Jaime Lorenzo{-}Trueba and
                  Thomas Merritt and
                  Thomas Drugman and
                  Srikanth Ronanki and
                  Viacheslav Klimkov},
  title        = {Effect of Data Reduction on Sequence-to-sequence Neural {TTS}},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
  pages        = {7075--7079},
  publisher    = {{IEEE}},
  year         = {2019},
  url          = {https://doi.org/10.1109/ICASSP.2019.8682168},
  doi          = {10.1109/ICASSP.2019.8682168},
  timestamp    = {Wed, 16 Oct 2019 14:14:52 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/LatorreLLMDRK19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Lorenzo-TruebaD19,
  author       = {Jaime Lorenzo{-}Trueba and
                  Thomas Drugman and
                  Javier Latorre and
                  Thomas Merritt and
                  Bartosz Putrycz and
                  Roberto Barra{-}Chicote and
                  Alexis Moinet and
                  Vatsal Aggarwal},
  editor       = {Gernot Kubin and
                  Zdravko Kacic},
  title        = {Towards Achieving Robust Universal Neural Vocoding},
  booktitle    = {Interspeech 2019, 20th Annual Conference of the International Speech
                  Communication Association, Graz, Austria, 15-19 September 2019},
  pages        = {181--185},
  publisher    = {{ISCA}},
  year         = {2019},
  url          = {https://doi.org/10.21437/Interspeech.2019-1424},
  doi          = {10.21437/INTERSPEECH.2019-1424},
  timestamp    = {Fri, 29 Jan 2021 17:41:10 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/Lorenzo-TruebaD19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/PrateekLBDLMRW19,
  author       = {Nishant Prateek and
                  Mateusz Lajszczak and
                  Roberto Barra{-}Chicote and
                  Thomas Drugman and
                  Jaime Lorenzo{-}Trueba and
                  Thomas Merritt and
                  Srikanth Ronanki and
                  Trevor Wood},
  editor       = {Anastassia Loukina and
                  Michelle Morales and
                  Rohit Kumar},
  title        = {In Other News: a Bi-style Text-to-speech Model for Synthesizing Newscaster
                  Voice with Limited Data},
  booktitle    = {Proceedings of the 2019 Conference of the North American Chapter of
                  the Association for Computational Linguistics: Human Language Technologies,
                  {NAACL-HLT} 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 2 (Industry
                  Papers)},
  pages        = {205--213},
  publisher    = {Association for Computational Linguistics},
  year         = {2019},
  url          = {https://doi.org/10.18653/v1/n19-2026},
  doi          = {10.18653/V1/N19-2026},
  timestamp    = {Fri, 06 Aug 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/naacl/PrateekLBDLMRW19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-02790,
  author       = {Nishant Prateek and
                  Mateusz Lajszczak and
                  Roberto Barra{-}Chicote and
                  Thomas Drugman and
                  Jaime Lorenzo{-}Trueba and
                  Thomas Merritt and
                  Srikanth Ronanki and
                  Trevor Wood},
  title        = {In Other News: {A} Bi-style Text-to-speech Model for Synthesizing
                  Newscaster Voice with Limited Data},
  journal      = {CoRR},
  volume       = {abs/1904.02790},
  year         = {2019},
  url          = {http://arxiv.org/abs/1904.02790},
  eprinttype    = {arXiv},
  eprint       = {1904.02790},
  timestamp    = {Wed, 24 Apr 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1904-02790.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-03952,
  author       = {Seyyed Saeed Sarfjoo and
                  Xin Wang and
                  Gustav Eje Henter and
                  Jaime Lorenzo{-}Trueba and
                  Shinji Takaki and
                  Junichi Yamagishi},
  title        = {Transformation of low-quality device-recorded speech to high-quality
                  speech using improved {SEGAN} model},
  journal      = {CoRR},
  volume       = {abs/1911.03952},
  year         = {2019},
  url          = {http://arxiv.org/abs/1911.03952},
  eprinttype    = {arXiv},
  eprint       = {1911.03952},
  timestamp    = {Fri, 17 Jul 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1911-03952.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-12760,
  author       = {Vatsal Aggarwal and
                  Marius Cotescu and
                  Nishant Prateek and
                  Jaime Lorenzo{-}Trueba and
                  Roberto Barra{-}Chicote},
  title        = {Using VAEs and Normalizing Flows for One-shot Text-To-Speech Synthesis
                  of Expressive Speech},
  journal      = {CoRR},
  volume       = {abs/1911.12760},
  year         = {2019},
  url          = {http://arxiv.org/abs/1911.12760},
  eprinttype    = {arXiv},
  eprint       = {1911.12760},
  timestamp    = {Wed, 08 Jan 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1911-12760.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-00955,
  author       = {Shubhi Tyagi and
                  Marco Nicolis and
                  Jonas Rohnke and
                  Thomas Drugman and
                  Jaime Lorenzo{-}Trueba},
  title        = {Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven
                  Acoustic Embedding Selection},
  journal      = {CoRR},
  volume       = {abs/1912.00955},
  year         = {2019},
  url          = {http://arxiv.org/abs/1912.00955},
  eprinttype    = {arXiv},
  eprint       = {1912.00955},
  timestamp    = {Thu, 02 Jan 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1912-00955.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-05289,
  author       = {Marius Cotescu and
                  Thomas Drugman and
                  Goeric Huybrechts and
                  Jaime Lorenzo{-}Trueba and
                  Alexis Moinet},
  title        = {Voice Conversion for Whispered Speech Synthesis},
  journal      = {CoRR},
  volume       = {abs/1912.05289},
  year         = {2019},
  url          = {http://arxiv.org/abs/1912.05289},
  eprinttype    = {arXiv},
  eprint       = {1912.05289},
  timestamp    = {Thu, 02 Jan 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1912-05289.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/Lorenzo-TruebaH18,
  author       = {Jaime Lorenzo{-}Trueba and
                  Gustav Eje Henter and
                  Shinji Takaki and
                  Junichi Yamagishi and
                  Yosuke Morino and
                  Yuta Ochiai},
  title        = {Investigating different representations for modeling and controlling
                  multiple emotions in DNN-based speech synthesis},
  journal      = {Speech Commun.},
  volume       = {99},
  pages        = {135--143},
  year         = {2018},
  url          = {https://doi.org/10.1016/j.specom.2018.03.002},
  doi          = {10.1016/J.SPECOM.2018.03.002},
  timestamp    = {Sat, 22 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/speech/Lorenzo-TruebaH18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HenterL0KY18,
  author       = {Gustav Eje Henter and
                  Jaime Lorenzo{-}Trueba and
                  Xin Wang and
                  Mariko Kondo and
                  Junichi Yamagishi},
  title        = {Cyborg Speech: Deep Multilingual Speech Synthesis for Generating Segmental
                  Foreign Accent with Natural Prosody},
  booktitle    = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  pages        = {4799--4803},
  publisher    = {{IEEE}},
  year         = {2018},
  url          = {https://doi.org/10.1109/ICASSP.2018.8462470},
  doi          = {10.1109/ICASSP.2018.8462470},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/HenterL0KY18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangLTJY18,
  author       = {Xin Wang and
                  Jaime Lorenzo{-}Trueba and
                  Shinji Takaki and
                  Lauri Juvela and
                  Junichi Yamagishi},
  title        = {A Comparison of Recent Waveform Generation and Acoustic Modeling Methods
                  for Neural-Network-Based Speech Synthesis},
  booktitle    = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  pages        = {4804--4808},
  publisher    = {{IEEE}},
  year         = {2018},
  url          = {https://doi.org/10.1109/ICASSP.2018.8461452},
  doi          = {10.1109/ICASSP.2018.8461452},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/WangLTJY18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/FangYEL18,
  author       = {Fuming Fang and
                  Junichi Yamagishi and
                  Isao Echizen and
                  Jaime Lorenzo{-}Trueba},
  title        = {High-Quality Nonparallel Voice Conversion Based on Cycle-Consistent
                  Adversarial Network},
  booktitle    = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  pages        = {5279--5283},
  publisher    = {{IEEE}},
  year         = {2018},
  url          = {https://doi.org/10.1109/ICASSP.2018.8462342},
  doi          = {10.1109/ICASSP.2018.8462342},
  timestamp    = {Tue, 18 Sep 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/FangYEL18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/JaukLYB18,
  author       = {Igor Jauk and
                  Jaime Lorenzo{-}Trueba and
                  Junichi Yamagishi and
                  Antonio Bonafonte},
  editor       = {B. Yegnanarayana},
  title        = {Expressive Speech Synthesis Using Sentiment Embeddings},
  booktitle    = {Interspeech 2018, 19th Annual Conference of the International Speech
                  Communication Association, Hyderabad, India, 2-6 September 2018},
  pages        = {3062--3066},
  publisher    = {{ISCA}},
  year         = {2018},
  url          = {https://doi.org/10.21437/Interspeech.2018-2467},
  doi          = {10.21437/INTERSPEECH.2018-2467},
  timestamp    = {Fri, 21 May 2021 08:16:43 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/JaukLYB18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/KinnunenLYTSVL18,
  author       = {Tomi Kinnunen and
                  Jaime Lorenzo{-}Trueba and
                  Junichi Yamagishi and
                  Tomoki Toda and
                  Daisuke Saito and
                  Fernando Villavicencio and
                  Zhen{-}Hua Ling},
  editor       = {Anthony Larcher and
                  Jean{-}Fran{\c{c}}ois Bonastre},
  title        = {A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging
                  from Spoofing Countermeasures for Speech Artifact Assessment},
  booktitle    = {Odyssey 2018: The Speaker and Language Recognition Workshop, 26-29
                  June 2018, Les Sables d'Olonne, France},
  pages        = {187--194},
  publisher    = {{ISCA}},
  year         = {2018},
  url          = {https://doi.org/10.21437/Odyssey.2018-27},
  doi          = {10.21437/ODYSSEY.2018-27},
  timestamp    = {Tue, 16 Nov 2021 11:36:04 +0100},
  biburl       = {https://dblp.org/rec/conf/odyssey/KinnunenLYTSVL18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/Lorenzo-TruebaY18,
  author       = {Jaime Lorenzo{-}Trueba and
                  Junichi Yamagishi and
                  Tomoki Toda and
                  Daisuke Saito and
                  Fernando Villavicencio and
                  Tomi Kinnunen and
                  Zhen{-}Hua Ling},
  editor       = {Anthony Larcher and
                  Jean{-}Fran{\c{c}}ois Bonastre},
  title        = {The Voice Conversion Challenge 2018: Promoting Development of Parallel
                  and Nonparallel Methods},
  booktitle    = {Odyssey 2018: The Speaker and Language Recognition Workshop, 26-29
                  June 2018, Les Sables d'Olonne, France},
  pages        = {195--202},
  publisher    = {{ISCA}},
  year         = {2018},
  url          = {https://doi.org/10.21437/Odyssey.2018-28},
  doi          = {10.21437/ODYSSEY.2018-28},
  timestamp    = {Wed, 10 Feb 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/odyssey/Lorenzo-TruebaY18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/Lorenzo-TruebaF18,
  author       = {Jaime Lorenzo{-}Trueba and
                  Fuming Fang and
                  Xin Wang and
                  Isao Echizen and
                  Junichi Yamagishi and
                  Tomi Kinnunen},
  editor       = {Anthony Larcher and
                  Jean{-}Fran{\c{c}}ois Bonastre},
  title        = {Can we steal your vocal identity from the Internet?: Initial investigation
                  of cloning Obama's voice using GAN, WaveNet and low-quality found
                  data},
  booktitle    = {Odyssey 2018: The Speaker and Language Recognition Workshop, 26-29
                  June 2018, Les Sables d'Olonne, France},
  pages        = {240--247},
  publisher    = {{ISCA}},
  year         = {2018},
  url          = {https://doi.org/10.21437/Odyssey.2018-34},
  doi          = {10.21437/ODYSSEY.2018-34},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/odyssey/Lorenzo-TruebaF18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-00860,
  author       = {Jaime Lorenzo{-}Trueba and
                  Fuming Fang and
                  Xin Wang and
                  Isao Echizen and
                  Junichi Yamagishi and
                  Tomi Kinnunen},
  title        = {Can we steal your vocal identity from the Internet?: Initial investigation
                  of cloning Obama's voice using GAN, WaveNet and low-quality found
                  data},
  journal      = {CoRR},
  volume       = {abs/1803.00860},
  year         = {2018},
  url          = {http://arxiv.org/abs/1803.00860},
  eprinttype    = {arXiv},
  eprint       = {1803.00860},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1803-00860.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-00425,
  author       = {Fuming Fang and
                  Junichi Yamagishi and
                  Isao Echizen and
                  Jaime Lorenzo{-}Trueba},
  title        = {High-quality nonparallel voice conversion based on cycle-consistent
                  adversarial network},
  journal      = {CoRR},
  volume       = {abs/1804.00425},
  year         = {2018},
  url          = {http://arxiv.org/abs/1804.00425},
  eprinttype    = {arXiv},
  eprint       = {1804.00425},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1804-00425.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-02549,
  author       = {Xin Wang and
                  Jaime Lorenzo{-}Trueba and
                  Shinji Takaki and
                  Lauri Juvela and
                  Junichi Yamagishi},
  title        = {A comparison of recent waveform generation and acoustic modeling methods
                  for neural-network-based speech synthesis},
  journal      = {CoRR},
  volume       = {abs/1804.02549},
  year         = {2018},
  url          = {http://arxiv.org/abs/1804.02549},
  eprinttype    = {arXiv},
  eprint       = {1804.02549},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1804-02549.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-04262,
  author       = {Jaime Lorenzo{-}Trueba and
                  Junichi Yamagishi and
                  Tomoki Toda and
                  Daisuke Saito and
                  Fernando Villavicencio and
                  Tomi Kinnunen and
                  Zhen{-}Hua Ling},
  title        = {The Voice Conversion Challenge 2018: Promoting Development of Parallel
                  and Nonparallel Methods},
  journal      = {CoRR},
  volume       = {abs/1804.04262},
  year         = {2018},
  url          = {http://arxiv.org/abs/1804.04262},
  eprinttype    = {arXiv},
  eprint       = {1804.04262},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1804-04262.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-08438,
  author       = {Tomi Kinnunen and
                  Jaime Lorenzo{-}Trueba and
                  Junichi Yamagishi and
                  Tomoki Toda and
                  Daisuke Saito and
                  Fernando Villavicencio and
                  Zhen{-}Hua Ling},
  title        = {A Spoofing Benchmark for the 2018 Voice Conversion Challenge: Leveraging
                  from Spoofing Countermeasures for Speech Artifact Assessment},
  journal      = {CoRR},
  volume       = {abs/1804.08438},
  year         = {2018},
  url          = {http://arxiv.org/abs/1804.08438},
  eprinttype    = {arXiv},
  eprint       = {1804.08438},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1804-08438.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-06292,
  author       = {Jaime Lorenzo{-}Trueba and
                  Thomas Drugman and
                  Javier Latorre and
                  Thomas Merritt and
                  Bartosz Putrycz and
                  Roberto Barra{-}Chicote},
  title        = {Robust universal neural vocoding},
  journal      = {CoRR},
  volume       = {abs/1811.06292},
  year         = {2018},
  url          = {http://arxiv.org/abs/1811.06292},
  eprinttype    = {arXiv},
  eprint       = {1811.06292},
  timestamp    = {Mon, 26 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1811-06292.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-06315,
  author       = {Javier Latorre and
                  Jakub Lachowicz and
                  Jaime Lorenzo{-}Trueba and
                  Thomas Merritt and
                  Thomas Drugman and
                  Srikanth Ronanki and
                  Klimkov Viacheslav},
  title        = {Effect of data reduction on sequence-to-sequence neural {TTS}},
  journal      = {CoRR},
  volume       = {abs/1811.06315},
  year         = {2018},
  url          = {http://arxiv.org/abs/1811.06315},
  eprinttype    = {arXiv},
  eprint       = {1811.06315},
  timestamp    = {Fri, 30 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1811-06315.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Lorenzo-TruebaV17,
  author       = {Jaime Lorenzo{-}Trueba and
                  Cassia Valentini{-}Botinhao and
                  Gustav Eje Henter and
                  Junichi Yamagishi},
  editor       = {Francisco Lacerda},
  title        = {Misperceptions of the Emotional Content of Natural and Vocoded Speech
                  in a Car},
  booktitle    = {Interspeech 2017, 18th Annual Conference of the International Speech
                  Communication Association, Stockholm, Sweden, August 20-24, 2017},
  pages        = {606--610},
  publisher    = {{ISCA}},
  year         = {2017},
  url          = {https://doi.org/10.21437/Interspeech.2017-532},
  doi          = {10.21437/INTERSPEECH.2017-532},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/Lorenzo-TruebaV17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HenterLWY17,
  author       = {Gustav Eje Henter and
                  Jaime Lorenzo{-}Trueba and
                  Xin Wang and
                  Junichi Yamagishi},
  editor       = {Francisco Lacerda},
  title        = {Principles for Learning Controllable {TTS} from Annotated and Latent
                  Variation},
  booktitle    = {Interspeech 2017, 18th Annual Conference of the International Speech
                  Communication Association, Stockholm, Sweden, August 20-24, 2017},
  pages        = {3956--3960},
  publisher    = {{ISCA}},
  year         = {2017},
  url          = {https://doi.org/10.21437/Interspeech.2017-171},
  doi          = {10.21437/INTERSPEECH.2017-171},
  timestamp    = {Sun, 06 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/HenterLWY17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/percom/San-Segundo-Hernandez16,
  author       = {Rub{\'{e}}n San{-}Segundo{-}Hern{\'{a}}ndez and
                  Jaime Lorenzo{-}Trueba and
                  Beatriz Mart{\'{\i}}nez{-}Gonz{\'{a}}lez and
                  Jos{\'{e}} M. Pardo},
  title        = {Segmenting human activities based on HMMs using smartphone inertial
                  sensors},
  journal      = {Pervasive Mob. Comput.},
  volume       = {30},
  pages        = {84--96},
  year         = {2016},
  url          = {https://doi.org/10.1016/j.pmcj.2016.01.004},
  doi          = {10.1016/J.PMCJ.2016.01.004},
  timestamp    = {Sat, 22 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/percom/San-Segundo-Hernandez16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/coling/Lorenzo-TruebaB16,
  author       = {Jaime Lorenzo{-}Trueba and
                  Roberto Barra{-}Chicote and
                  Ascensi{\'{o}}n Gallardo{-}Antol{\'{\i}}n and
                  Junichi Yamagishi and
                  Juan Manuel Montero},
  editor       = {Nicoletta Calzolari and
                  Yuji Matsumoto and
                  Rashmi Prasad},
  title        = {Continuous Expressive Speaking Styles Synthesis based on {CVSM} and
                  {MR-HMM}},
  booktitle    = {{COLING} 2016, 26th International Conference on Computational Linguistics,
                  Proceedings of the Conference: Technical Papers, December 11-16, 2016,
                  Osaka, Japan},
  pages        = {369--376},
  publisher    = {{ACL}},
  year         = {2016},
  url          = {https://aclanthology.org/C16-1036/},
  timestamp    = {Fri, 06 Aug 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/coling/Lorenzo-TruebaB16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csl/Lorenzo-TruebaB15,
  author       = {Jaime Lorenzo{-}Trueba and
                  Roberto Barra{-}Chicote and
                  Rub{\'{e}}n San Segundo and
                  Javier Ferreiros and
                  Junichi Yamagishi and
                  Juan Manuel Montero},
  title        = {Emotion transplantation through adaptation in HMM-based speech synthesis},
  journal      = {Comput. Speech Lang.},
  volume       = {34},
  number       = {1},
  pages        = {292--307},
  year         = {2015},
  url          = {https://doi.org/10.1016/j.csl.2015.03.008},
  doi          = {10.1016/J.CSL.2015.03.008},
  timestamp    = {Sat, 05 Sep 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/csl/Lorenzo-TruebaB15.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iberspeech/Lorenzo-TruebaBYM14,
  author       = {Jaime Lorenzo{-}Trueba and
                  Roberto Barra{-}Chicote and
                  Junichi Yamagishi and
                  Juan Manuel Montero},
  editor       = {Juan Luis Navarro Mesa and
                  Alfonso Ortega and
                  Ant{\'{o}}nio J. S. Teixeira and
                  Eduardo Hern{\'{a}}ndez{-}P{\'{e}}rez and
                  Pedro J. Quintana{-}Morales and
                  Antonio G. Ravelo{-}Garc{\'{\i}}a and
                  Iv{\'{a}}n Guerra Moreno and
                  Doroteo T. Toledano},
  title        = {Towards Cross-Lingual Emotion Transplantation},
  booktitle    = {Advances in Speech and Language Technologies for Iberian Languages
                  - Second International Conference, IberSPEECH 2014, Las Palmas de
                  Gran Canaria, Spain, November 19-21, 2014. Proceedings},
  series       = {Lecture Notes in Computer Science},
  volume       = {8854},
  pages        = {199--208},
  publisher    = {Springer},
  year         = {2014},
  url          = {https://doi.org/10.1007/978-3-319-13623-3\_21},
  doi          = {10.1007/978-3-319-13623-3\_21},
  timestamp    = {Thu, 23 Jun 2022 19:58:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iberspeech/Lorenzo-TruebaBYM14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Lorenzo-TruebaE14,
  author       = {Jaime Lorenzo{-}Trueba and
                  Juli{\'{a}}n D. Echeverry{-}Correa and
                  Roberto Barra{-}Chicote and
                  Rub{\'{e}}n San{-}Segundo{-}Hern{\'{a}}ndez and
                  Javier Ferreiros and
                  Ascensi{\'{o}}n Gallardo{-}Antol{\'{\i}}n and
                  Junichi Yamagishi and
                  Simon King and
                  Juan Manuel Montero{-}Mart{\'{\i}}nez},
  title        = {Development of a genre-dependent {TTS} system with cross-speaker speaking-style
                  transplantation},
  booktitle    = {2nd International Workshop on Speech, Language and Audio in Multimedia,
                  {SLAM} 2014, Penang, Malaysia, September 11-12, 2014},
  pages        = {39--42},
  publisher    = {{ISCA}},
  year         = {2014},
  url          = {http://www.isca-speech.org/archive/slam\_2014/slm4\_039.html},
  timestamp    = {Fri, 02 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/Lorenzo-TruebaE14.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sensors/LutfiFLBM13,
  author       = {Syaheerah Lebai Lutfi and
                  Fernando Fern{\'{a}}ndez Mart{\'{\i}}nez and
                  Jaime Lorenzo{-}Trueba and
                  Roberto Barra{-}Chicote and
                  Juan Manuel Montero},
  title        = {I \emph{Feel} You: The Design and Evaluation of a Domotic Affect-Sensitive
                  Spoken Conversational Agent},
  journal      = {Sensors},
  volume       = {13},
  number       = {8},
  pages        = {10519--10538},
  year         = {2013},
  url          = {https://doi.org/10.3390/s130810519},
  doi          = {10.3390/S130810519},
  timestamp    = {Wed, 13 Jan 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/sensors/LutfiFLBM13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmi/LutfiFLBM13,
  author       = {Syaheerah Lebai Lutfi and
                  Fernando Fern{\'{a}}ndez Mart{\'{\i}}nez and
                  Jaime Lorenzo{-}Trueba and
                  Roberto Barra{-}Chicote and
                  Juan Manuel Montero},
  editor       = {Julien Epps and
                  Fang Chen and
                  Sharon L. Oviatt and
                  Kenji Mase and
                  Andrew Sears and
                  Kristiina Jokinen and
                  Bj{\"{o}}rn W. Schuller},
  title        = {{NEMOHIFI:} an affective HiFi agent},
  booktitle    = {2013 International Conference on Multimodal Interaction, {ICMI} '13,
                  Sydney, NSW, Australia, December 9-13, 2013},
  pages        = {319--320},
  publisher    = {{ACM}},
  year         = {2013},
  url          = {https://doi.org/10.1145/2522848.2531755},
  doi          = {10.1145/2522848.2531755},
  timestamp    = {Wed, 13 Jan 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icmi/LutfiFLBM13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ssw/Lorenzo-TruebaB13,
  author       = {Jaime Lorenzo{-}Trueba and
                  Roberto Barra{-}Chicote and
                  Junichi Yamagishi and
                  Oliver Watts and
                  Juan Manuel Montero},
  title        = {Towards speaking style transplantation in speech synthesis},
  booktitle    = {The Eighth {ISCA} Tutorial and Research Workshop on Speech Synthesis,
                  Barcelona, Spain, August 31-September 2, 2013},
  pages        = {159--163},
  publisher    = {{ISCA}},
  year         = {2013},
  url          = {http://www.isca-speech.org/archive/ssw8/ssw8\_159.html},
  timestamp    = {Tue, 16 Nov 2021 11:36:18 +0100},
  biburl       = {https://dblp.org/rec/conf/ssw/Lorenzo-TruebaB13.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pdln/Lopez-LudenaSML12,
  author       = {Ver{\'{o}}nica L{\'{o}}pez{-}Lude{\~{n}}a and
                  Rub{\'{e}}n San Segundo and
                  Juan Manuel Montero and
                  Jaime Lorenzo{-}Trueba},
  title        = {Sentence selection for improving the tuning process of a statistical
                  machine translation system},
  journal      = {Proces. del Leng. Natural},
  volume       = {48},
  pages        = {51--56},
  year         = {2012},
  url          = {http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/4487},
  timestamp    = {Wed, 17 Feb 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pdln/Lopez-LudenaSML12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Lorenzo-TruebaBROAYM12,
  author       = {Jaime Lorenzo{-}Trueba and
                  Roberto Barra{-}Chicote and
                  Tuomo Raitio and
                  Nicolas Obin and
                  Paavo Alku and
                  Junichi Yamagishi and
                  Juan Manuel Montero},
  title        = {Towards Glottal Source Controllability in Expressive Speech Synthesis},
  booktitle    = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
                  Communication Association, Portland, Oregon, USA, September 9-13,
                  2012},
  pages        = {1620--1623},
  publisher    = {{ISCA}},
  year         = {2012},
  url          = {https://doi.org/10.21437/Interspeech.2012-445},
  doi          = {10.21437/INTERSPEECH.2012-445},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/Lorenzo-TruebaBROAYM12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LorenzoMBLFYM12,
  author       = {Jaime Lorenzo{-}Trueba and
                  Beatriz Mart{\'{\i}}nez{-}Gonz{\'{a}}lez and
                  Roberto Barra{-}Chicote and
                  Ver{\'{o}}nica L{\'{o}}pez{-}Lude{\~{n}}a and
                  Javier Ferreiros and
                  Junichi Yamagishi and
                  Juan Manuel Montero},
  title        = {Towards an Unsupervised Speaking Style Voice Building Framework: Multi-Style
                  Speaker Diarization},
  booktitle    = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
                  Communication Association, Portland, Oregon, USA, September 9-13,
                  2012},
  pages        = {2278--2281},
  publisher    = {{ISCA}},
  year         = {2012},
  url          = {https://doi.org/10.21437/Interspeech.2012-598},
  doi          = {10.21437/INTERSPEECH.2012-598},
  timestamp    = {Fri, 23 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/LorenzoMBLFYM12.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
a service of  Schloss Dagstuhl - Leibniz Center for Informatics