default search action
BibTeX records: David Rybach
@inproceedings{DBLP:conf/icassp/ChenAHPRHCARMR23, author = {Tongzhou Chen and Cyril Allauzen and Yinghui Huang and Daniel S. Park and David Rybach and W. Ronny Huang and Rodrigo Cabrera and Kartik Audhkhasi and Bhuvana Ramabhadran and Pedro J. Moreno and Michael Riley}, title = {Large-Scale Language Model Rescoring on Long-Form Data}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10096429}, doi = {10.1109/ICASSP49357.2023.10096429}, timestamp = {Sun, 05 Nov 2023 16:51:21 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ChenAHPRHCARMR23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HuangCSHRDPAPS23, author = {W. Ronny Huang and Shuo{-}Yiin Chang and Tara N. Sainath and Yanzhang He and David Rybach and Robert David and Rohit Prabhavalkar and Cyril Allauzen and Cal Peyser and Trevor D. Strohman}, title = {{E2E} Segmentation in a Two-Pass Cascaded Encoder {ASR} Model}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10095355}, doi = {10.1109/ICASSP49357.2023.10095355}, timestamp = {Sun, 05 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/HuangCSHRDPAPS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/VarianiWRAR23, author = {Ehsan Variani and Ke Wu and David Rybach and Cyril Allauzen and Michael Riley}, title = {Alignment Entropy Regularization}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10095813}, doi = {10.1109/ICASSP49357.2023.10095813}, timestamp = {Sun, 05 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/VarianiWRAR23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WangZDZCRSHMK23, author = {Weiran Wang and Ding Zhao and Shaojin Ding and Hao Zhang and Shuo{-}Yiin Chang and David Rybach and Tara N. Sainath and Yanzhang He and Ian McGraw and Shankar Kumar}, title = {Multi-Output {RNN-T} Joint Networks for Multi-Task Learning of {ASR} and Auxiliary Tasks}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10096273}, doi = {10.1109/ICASSP49357.2023.10096273}, timestamp = {Sun, 21 Jul 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/WangZDZCRSHMK23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-08133, author = {Tongzhou Chen and Cyril Allauzen and Yinghui Huang and Daniel S. Park and David Rybach and W. Ronny Huang and Rodrigo Cabrera and Kartik Audhkhasi and Bhuvana Ramabhadran and Pedro J. Moreno and Michael Riley}, title = {Large-scale Language Model Rescoring on Long-form Data}, journal = {CoRR}, volume = {abs/2306.08133}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.08133}, doi = {10.48550/ARXIV.2306.08133}, eprinttype = {arXiv}, eprint = {2306.08133}, timestamp = {Mon, 19 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-08133.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SainathHNBWQCPG22, author = {Tara N. Sainath and Yanzhang He and Arun Narayanan and Rami Botros and Weiran Wang and David Qiu and Chung{-}Cheng Chiu and Rohit Prabhavalkar and Alexander Gruenstein and Anmol Gulati and Bo Li and David Rybach and Emmanuel Guzman and Ian McGraw and James Qin and Krzysztof Choromanski and Qiao Liang and Robert David and Ruoming Pang and Shuo{-}Yiin Chang and Trevor Strohman and W. Ronny Huang and Wei Han and Yonghui Wu and Yu Zhang}, title = {Improving The Latency And Quality Of Cascaded Encoders}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {8112--8116}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747879}, doi = {10.1109/ICASSP43922.2022.9747879}, timestamp = {Tue, 07 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/SainathHNBWQCPG22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WangCSVPHRGMPSH22, author = {Weiran Wang and Tongzhou Chen and Tara N. Sainath and Ehsan Variani and Rohit Prabhavalkar and W. Ronny Huang and Bhuvana Ramabhadran and Neeraj Gaur and Sepand Mavandadi and Cal Peyser and Trevor Strohman and Yanzhang He and David Rybach}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Improving Rare Word Recognition with LM-aware {MWER} Training}, booktitle = {23rd Annual Conference of the International Speech Communication Association, Interspeech 2022, Incheon, Korea, September 18-22, 2022}, pages = {1031--1035}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-10660}, doi = {10.21437/INTERSPEECH.2022-10660}, timestamp = {Tue, 11 Jun 2024 16:45:43 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WangCSVPHRGMPSH22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/Variani0RACR22, author = {Ehsan Variani and Michael Riley and David Rybach and Cyril Allauzen and Tongzhou Chen and Bhuvana Ramabhadran}, editor = {Hanseok Ko and John H. L. Hansen}, title = {On Adaptive Weight Interpolation of the Hybrid Autoregressive Transducer}, booktitle = {23rd Annual Conference of the International Speech Communication Association, Interspeech 2022, Incheon, Korea, September 18-22, 2022}, pages = {1646--1650}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-4}, doi = {10.21437/INTERSPEECH.2022-4}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/Variani0RACR22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HuangCRSPPLA22, author = {W. Ronny Huang and Shuo{-}Yiin Chang and David Rybach and Tara N. Sainath and Rohit Prabhavalkar and Cal Peyser and Zhiyun Lu and Cyril Allauzen}, editor = {Hanseok Ko and John H. L. Hansen}, title = {{E2E} Segmenter: Joint Segmenting and Decoding for Long-Form {ASR}}, booktitle = {23rd Annual Conference of the International Speech Communication Association, Interspeech 2022, Incheon, Korea, September 18-22, 2022}, pages = {4995--4999}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-38}, doi = {10.21437/INTERSPEECH.2022-38}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HuangCRSPPLA22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/VarianiWRRSA22, author = {Ehsan Variani and Ke Wu and Michael D. Riley and David Rybach and Matt Shannon and Cyril Allauzen}, editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh}, title = {Global Normalization for Streaming Speech Recognition in a Modular Framework}, booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022}, year = {2022}, url = {http://papers.nips.cc/paper\_files/paper/2022/hash/1b4839ff1f843b6be059bd0e8437e975-Abstract-Conference.html}, timestamp = {Mon, 08 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/VarianiWRRSA22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-06469, author = {Andreas Kabel and Keith B. Hall and Tom Ouyang and David Rybach and Daan van Esch and Fran{\c{c}}oise Beaufays}, title = {Handling Compounding in Mobile Keyboard Input}, journal = {CoRR}, volume = {abs/2201.06469}, year = {2022}, url = {https://arxiv.org/abs/2201.06469}, eprinttype = {arXiv}, eprint = {2201.06469}, timestamp = {Fri, 21 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-06469.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2204-07553, author = {Weiran Wang and Tongzhou Chen and Tara N. Sainath and Ehsan Variani and Rohit Prabhavalkar and W. Ronny Huang and Bhuvana Ramabhadran and Neeraj Gaur and Sepand Mavandadi and Cal Peyser and Trevor Strohman and Yanzhang He and David Rybach}, title = {Improving Rare Word Recognition with LM-aware {MWER} Training}, journal = {CoRR}, volume = {abs/2204.07553}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2204.07553}, doi = {10.48550/ARXIV.2204.07553}, eprinttype = {arXiv}, eprint = {2204.07553}, timestamp = {Tue, 19 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2204-07553.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2204-10749, author = {W. Ronny Huang and Shuo{-}Yiin Chang and David Rybach and Rohit Prabhavalkar and Tara N. Sainath and Cyril Allauzen and Cal Peyser and Zhiyun Lu}, title = {{E2E} Segmenter: Joint Segmenting and Decoding for Long-Form {ASR}}, journal = {CoRR}, volume = {abs/2204.10749}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2204.10749}, doi = {10.48550/ARXIV.2204.10749}, eprinttype = {arXiv}, eprint = {2204.10749}, timestamp = {Mon, 25 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2204-10749.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-13674, author = {Ehsan Variani and Ke Wu and Michael Riley and David Rybach and Matt Shannon and Cyril Allauzen}, title = {Global Normalization for Streaming Speech Recognition in a Modular Framework}, journal = {CoRR}, volume = {abs/2205.13674}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.13674}, doi = {10.48550/ARXIV.2205.13674}, eprinttype = {arXiv}, eprint = {2205.13674}, timestamp = {Tue, 31 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-13674.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-15432, author = {W. Ronny Huang and Shuo{-}Yiin Chang and Tara N. Sainath and Yanzhang He and David Rybach and Robert David and Rohit Prabhavalkar and Cyril Allauzen and Cal Peyser and Trevor D. Strohman}, title = {{E2E} Segmentation in a Two-Pass Cascaded Encoder {ASR} Model}, journal = {CoRR}, volume = {abs/2211.15432}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.15432}, doi = {10.48550/ARXIV.2211.15432}, eprinttype = {arXiv}, eprint = {2211.15432}, timestamp = {Tue, 29 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-15432.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2212-12442, author = {Ehsan Variani and Ke Wu and David Rybach and Cyril Allauzen and Michael Riley}, title = {Alignment Entropy Regularization}, journal = {CoRR}, volume = {abs/2212.12442}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2212.12442}, doi = {10.48550/ARXIV.2212.12442}, eprinttype = {arXiv}, eprint = {2212.12442}, timestamp = {Wed, 04 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2212-12442.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/PrabhavalkarHRC21, author = {Rohit Prabhavalkar and Yanzhang He and David Rybach and Sean Campbell and Arun Narayanan and Trevor Strohman and Tara N. Sainath}, title = {Less is More: Improved {RNN-T} Decoding Using Limited Label Context and Path Merging}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {5659--5663}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9414212}, doi = {10.1109/ICASSP39728.2021.9414212}, timestamp = {Fri, 09 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/PrabhavalkarHRC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SainathHNBPRAVQ21, author = {Tara N. Sainath and Yanzhang He and Arun Narayanan and Rami Botros and Ruoming Pang and David Rybach and Cyril Allauzen and Ehsan Variani and James Qin and Quoc{-}Nam Le{-}The and Shuo{-}Yiin Chang and Bo Li and Anmol Gulati and Jiahui Yu and Chung{-}Cheng Chiu and Diamantino Caseiro and Wei Li and Qiao Liang and Pat Rondon}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling}, booktitle = {22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021}, pages = {1777--1781}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-206}, doi = {10.21437/INTERSPEECH.2021-206}, timestamp = {Tue, 11 Jun 2024 16:45:43 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SainathHNBPRAVQ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HuangSPKRS21, author = {W. Ronny Huang and Tara N. Sainath and Cal Peyser and Shankar Kumar and David Rybach and Trevor Strohman}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {Lookup-Table Recurrent Language Models for Long Tail Speech Recognition}, booktitle = {22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021}, pages = {2002--2006}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-340}, doi = {10.21437/INTERSPEECH.2021-340}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HuangSPKRS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/AllauzenV0RZ21, author = {Cyril Allauzen and Ehsan Variani and Michael Riley and David Rybach and Hao Zhang}, 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 Hybrid Seq-2-Seq {ASR} Design for On-Device and Server Applications}, booktitle = {22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021}, pages = {4044--4048}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-658}, doi = {10.21437/INTERSPEECH.2021-658}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/AllauzenV0RZ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2104-04552, author = {W. Ronny Huang and Tara N. Sainath and Cal Peyser and Shankar Kumar and David Rybach and Trevor Strohman}, title = {Lookup-Table Recurrent Language Models for Long Tail Speech Recognition}, journal = {CoRR}, volume = {abs/2104.04552}, year = {2021}, url = {https://arxiv.org/abs/2104.04552}, eprinttype = {arXiv}, eprint = {2104.04552}, timestamp = {Mon, 19 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2104-04552.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SainathHLNPBCLA20, author = {Tara N. Sainath and Yanzhang He and Bo Li and Arun Narayanan and Ruoming Pang and Antoine Bruguier and Shuo{-}Yiin Chang and Wei Li and Raziel Alvarez and Zhifeng Chen and Chung{-}Cheng Chiu and David Garcia and Alexander Gruenstein and Ke Hu and Anjuli Kannan and Qiao Liang and Ian McGraw and Cal Peyser and Rohit Prabhavalkar and Golan Pundak and David Rybach and Yuan Shangguan and Yash Sheth and Trevor Strohman and Mirk{\'{o}} Visontai and Yonghui Wu and Yu Zhang and Ding Zhao}, title = {A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {6059--6063}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9054188}, doi = {10.1109/ICASSP40776.2020.9054188}, timestamp = {Tue, 07 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/SainathHLNPBCLA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/VarianiRA020, author = {Ehsan Variani and David Rybach and Cyril Allauzen and Michael Riley}, title = {Hybrid Autoregressive Transducer {(HAT)}}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {6139--6143}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9053600}, doi = {10.1109/ICASSP40776.2020.9053600}, timestamp = {Thu, 23 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/VarianiRA020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/Chang0RHLSS20, author = {Shuo{-}Yiin Chang and Bo Li and David Rybach and Yanzhang He and Wei Li and Tara N. Sainath and Trevor Strohman}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Low Latency Speech Recognition Using End-to-End Prefetching}, booktitle = {21st Annual Conference of the International Speech Communication Association, Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020}, pages = {1962--1966}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-1898}, doi = {10.21437/INTERSPEECH.2020-1898}, timestamp = {Tue, 11 Jun 2024 16:45:43 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/Chang0RHLSS20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SainathPRGS20, author = {Tara N. Sainath and Ruoming Pang and David Rybach and Basi Garc{\'{\i}}a and Trevor Strohman}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Emitting Word Timings with End-to-End Models}, booktitle = {21st Annual Conference of the International Speech Communication Association, Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020}, pages = {3615--3619}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-1059}, doi = {10.21437/INTERSPEECH.2020-1059}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/SainathPRGS20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-07705, author = {Ehsan Variani and David Rybach and Cyril Allauzen and Michael Riley}, title = {Hybrid Autoregressive Transducer (hat)}, journal = {CoRR}, volume = {abs/2003.07705}, year = {2020}, url = {https://arxiv.org/abs/2003.07705}, eprinttype = {arXiv}, eprint = {2003.07705}, timestamp = {Tue, 24 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-07705.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-12710, author = {Tara N. Sainath and Yanzhang He and Bo Li and Arun Narayanan and Ruoming Pang and Antoine Bruguier and Shuo{-}Yiin Chang and Wei Li and Raziel Alvarez and Zhifeng Chen and Chung{-}Cheng Chiu and David Garcia and Alexander Gruenstein and Ke Hu and Minho Jin and Anjuli Kannan and Qiao Liang and Ian McGraw and Cal Peyser and Rohit Prabhavalkar and Golan Pundak and David Rybach and Yuan Shangguan and Yash Sheth and Trevor Strohman and Mirk{\'{o}} Visontai and Yonghui Wu and Yu Zhang and Ding Zhao}, title = {A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency}, journal = {CoRR}, volume = {abs/2003.12710}, year = {2020}, url = {https://arxiv.org/abs/2003.12710}, eprinttype = {arXiv}, eprint = {2003.12710}, timestamp = {Tue, 07 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-12710.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2012-06749, author = {Rohit Prabhavalkar and Yanzhang He and David Rybach and Sean Campbell and Arun Narayanan and Trevor Strohman and Tara N. Sainath}, title = {Less Is More: Improved {RNN-T} Decoding Using Limited Label Context and Path Merging}, journal = {CoRR}, volume = {abs/2012.06749}, year = {2020}, url = {https://arxiv.org/abs/2012.06749}, eprinttype = {arXiv}, eprint = {2012.06749}, timestamp = {Sat, 02 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2012-06749.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/NarayananPCRSS19, author = {Arun Narayanan and Rohit Prabhavalkar and Chung{-}Cheng Chiu and David Rybach and Tara N. Sainath and Trevor Strohman}, title = {Recognizing Long-Form Speech Using Streaming End-to-End Models}, booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2019, Singapore, December 14-18, 2019}, pages = {920--927}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ASRU46091.2019.9003913}, doi = {10.1109/ASRU46091.2019.9003913}, timestamp = {Mon, 24 Feb 2020 17:51:31 +0100}, biburl = {https://dblp.org/rec/conf/asru/NarayananPCRSS19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HeSPMAZRKWPLBSL19, author = {Yanzhang He and Tara N. Sainath and Rohit Prabhavalkar and Ian McGraw and Raziel Alvarez and Ding Zhao and David Rybach and Anjuli Kannan and Yonghui Wu and Ruoming Pang and Qiao Liang and Deepti Bhatia and Yuan Shangguan and Bo Li and Golan Pundak and Khe Chai Sim and Tom Bagby and Shuo{-}Yiin Chang and Kanishka Rao and Alexander Gruenstein}, title = {Streaming End-to-end Speech Recognition for Mobile Devices}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019}, pages = {6381--6385}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICASSP.2019.8682336}, doi = {10.1109/ICASSP.2019.8682336}, timestamp = {Tue, 07 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/HeSPMAZRKWPLBSL19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZhaoSRRBLP19, author = {Ding Zhao and Tara N. Sainath and David Rybach and Pat Rondon and Deepti Bhatia and Bo Li and Ruoming Pang}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Shallow-Fusion End-to-End Contextual Biasing}, booktitle = {20th Annual Conference of the International Speech Communication Association, Interspeech 2019, Graz, Austria, September 15-19, 2019}, pages = {1418--1422}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1209}, doi = {10.21437/INTERSPEECH.2019-1209}, timestamp = {Tue, 11 Jun 2024 16:45:43 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ZhaoSRRBLP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SainathPRHPLVLS19, author = {Tara N. Sainath and Ruoming Pang and David Rybach and Yanzhang He and Rohit Prabhavalkar and Wei Li and Mirk{\'{o}} Visontai and Qiao Liang and Trevor Strohman and Yonghui Wu and Ian McGraw and Chung{-}Cheng Chiu}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Two-Pass End-to-End Speech Recognition}, booktitle = {20th Annual Conference of the International Speech Communication Association, Interspeech 2019, Graz, Austria, September 15-19, 2019}, pages = {2773--2777}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1341}, doi = {10.21437/INTERSPEECH.2019-1341}, timestamp = {Tue, 07 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/SainathPRHPLVLS19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/IriePKBRN19, author = {Kazuki Irie and Rohit Prabhavalkar and Anjuli Kannan and Antoine Bruguier and David Rybach and Patrick Nguyen}, editor = {Gernot Kubin and Zdravko Kacic}, title = {On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition}, booktitle = {20th Annual Conference of the International Speech Communication Association, Interspeech 2019, Graz, Austria, September 15-19, 2019}, pages = {3800--3804}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-2277}, doi = {10.21437/INTERSPEECH.2019-2277}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/IriePKBRN19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1902-01955, author = {Kazuki Irie and Rohit Prabhavalkar and Anjuli Kannan and Antoine Bruguier and David Rybach and Patrick Nguyen}, title = {Model Unit Exploration for Sequence-to-Sequence Speech Recognition}, journal = {CoRR}, volume = {abs/1902.01955}, year = {2019}, url = {http://arxiv.org/abs/1902.01955}, eprinttype = {arXiv}, eprint = {1902.01955}, timestamp = {Tue, 21 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1902-01955.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1902-08295, author = {Jonathan Shen and Patrick Nguyen and Yonghui Wu and Zhifeng Chen and Mia Xu Chen and Ye Jia and Anjuli Kannan and Tara N. Sainath and Yuan Cao and Chung{-}Cheng Chiu and Yanzhang He and Jan Chorowski and Smit Hinsu and Stella Laurenzo and James Qin and Orhan Firat and Wolfgang Macherey and Suyog Gupta and Ankur Bapna and Shuyuan Zhang and Ruoming Pang and Ron J. Weiss and Rohit Prabhavalkar and Qiao Liang and Benoit Jacob and Bowen Liang and HyoukJoong Lee and Ciprian Chelba and S{\'{e}}bastien Jean and Bo Li and Melvin Johnson and Rohan Anil and Rajat Tibrewal and Xiaobing Liu and Akiko Eriguchi and Navdeep Jaitly and Naveen Ari and Colin Cherry and Parisa Haghani and Otavio Good and Youlong Cheng and Raziel Alvarez and Isaac Caswell and Wei{-}Ning Hsu and Zongheng Yang and Kuan{-}Chieh Wang and Ekaterina Gonina and Katrin Tomanek and Ben Vanik and Zelin Wu and Llion Jones and Mike Schuster and Yanping Huang and Dehao Chen and Kazuki Irie and George F. Foster and John Richardson and Klaus Macherey and Antoine Bruguier and Heiga Zen and Colin Raffel and Shankar Kumar and Kanishka Rao and David Rybach and Matthew Murray and Vijayaditya Peddinti and Maxim Krikun and Michiel Bacchiani and Thomas B. Jablin and Robert Suderman and Ian Williams and Benjamin Lee and Deepti Bhatia and Justin Carlson and Semih Yavuz and Yu Zhang and Ian McGraw and Max Galkin and Qi Ge and Golan Pundak and Chad Whipkey and Todd Wang and Uri Alon and Dmitry Lepikhin and Ye Tian and Sara Sabour and William Chan and Shubham Toshniwal and Baohua Liao and Michael Nirschl and Pat Rondon}, title = {Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling}, journal = {CoRR}, volume = {abs/1902.08295}, year = {2019}, url = {http://arxiv.org/abs/1902.08295}, eprinttype = {arXiv}, eprint = {1902.08295}, timestamp = {Tue, 07 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1902-08295.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1908-10992, author = {Tara N. Sainath and Ruoming Pang and David Rybach and Yanzhang He and Rohit Prabhavalkar and Wei Li and Mirk{\'{o}} Visontai and Qiao Liang and Trevor Strohman and Yonghui Wu and Ian McGraw and Chung{-}Cheng Chiu}, title = {Two-Pass End-to-End Speech Recognition}, journal = {CoRR}, volume = {abs/1908.10992}, year = {2019}, url = {http://arxiv.org/abs/1908.10992}, eprinttype = {arXiv}, eprint = {1908.10992}, timestamp = {Tue, 07 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1908-10992.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1910-11455, author = {Arun Narayanan and Rohit Prabhavalkar and Chung{-}Cheng Chiu and David Rybach and Tara N. Sainath and Trevor Strohman}, title = {Recognizing long-form speech using streaming end-to-end models}, journal = {CoRR}, volume = {abs/1910.11455}, year = {2019}, url = {http://arxiv.org/abs/1910.11455}, eprinttype = {arXiv}, eprint = {1910.11455}, timestamp = {Thu, 31 Oct 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1910-11455.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SainathPKLKRSNL18, author = {Tara N. Sainath and Rohit Prabhavalkar and Shankar Kumar and Seungji Lee and Anjuli Kannan and David Rybach and Vlad Schogol and Patrick Nguyen and Bo Li and Yonghui Wu and Zhifeng Chen and Chung{-}Cheng Chiu}, title = {No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models}, booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018}, pages = {5859--5863}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICASSP.2018.8462380}, doi = {10.1109/ICASSP.2018.8462380}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/SainathPKLKRSNL18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WilliamsKARS18, author = {Ian Williams and Anjuli Kannan and Petar S. Aleksic and David Rybach and Tara N. Sainath}, editor = {B. Yegnanarayana}, title = {Contextual Speech Recognition in End-to-end Neural Network Systems Using Beam Search}, booktitle = {19th Annual Conference of the International Speech Communication Association, Interspeech 2018, Hyderabad, India, September 2-6, 2018}, pages = {2227--2231}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Interspeech.2018-2416}, doi = {10.21437/INTERSPEECH.2018-2416}, timestamp = {Tue, 11 Jun 2024 16:45:43 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WilliamsKARS18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1811-06621, author = {Yanzhang He and Tara N. Sainath and Rohit Prabhavalkar and Ian McGraw and Raziel Alvarez and Ding Zhao and David Rybach and Anjuli Kannan and Yonghui Wu and Ruoming Pang and Qiao Liang and Deepti Bhatia and Yuan Shangguan and Bo Li and Golan Pundak and Khe Chai Sim and Tom Bagby and Shuo{-}Yiin Chang and Kanishka Rao and Alexander Gruenstein}, title = {Streaming End-to-end Speech Recognition For Mobile Devices}, journal = {CoRR}, volume = {abs/1811.06621}, year = {2018}, url = {http://arxiv.org/abs/1811.06621}, eprinttype = {arXiv}, eprint = {1811.06621}, timestamp = {Tue, 07 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1811-06621.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/RybachRS17, author = {David Rybach and Michael Riley and Johan Schalkwyk}, title = {On lattice generation for large vocabulary speech recognition}, booktitle = {2017 {IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2017, Okinawa, Japan, December 16-20, 2017}, pages = {228--235}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ASRU.2017.8268940}, doi = {10.1109/ASRU.2017.8268940}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/asru/RybachRS17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/fsmnlp/HellstenRGABORR17, author = {Lars Hellsten and Brian Roark and Prasoon Goyal and Cyril Allauzen and Fran{\c{c}}oise Beaufays and Tom Ouyang and Michael Riley and David Rybach}, editor = {Frank Drewes}, title = {Transliterated Mobile Keyboard Input via Weighted Finite-State Transducers}, booktitle = {Proceedings of the 13th International Conference on Finite State Methods and Natural Language Processing, {FSMNLP} 2017, Ume{\aa}, Sweden, September 2017}, pages = {10--19}, publisher = {Association for Computational Linguistics}, year = {2017}, url = {https://doi.org/10.18653/v1/W17-4002}, doi = {10.18653/V1/W17-4002}, timestamp = {Fri, 06 Aug 2021 00:41:23 +0200}, biburl = {https://dblp.org/rec/conf/fsmnlp/HellstenRGABORR17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/OuyangRBR17, author = {Tom Ouyang and David Rybach and Fran{\c{c}}oise Beaufays and Michael Riley}, title = {Mobile Keyboard Input Decoding with Finite-State Transducers}, journal = {CoRR}, volume = {abs/1704.03987}, year = {2017}, url = {http://arxiv.org/abs/1704.03987}, eprinttype = {arXiv}, eprint = {1704.03987}, timestamp = {Tue, 16 Apr 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/OuyangRBR17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1712-01864, author = {Tara N. Sainath and Rohit Prabhavalkar and Shankar Kumar and Seungji Lee and Anjuli Kannan and David Rybach and Vlad Schogol and Patrick Nguyen and Bo Li and Yonghui Wu and Zhifeng Chen and Chung{-}Cheng Chiu}, title = {No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models}, journal = {CoRR}, volume = {abs/1712.01864}, year = {2017}, url = {http://arxiv.org/abs/1712.01864}, eprinttype = {arXiv}, eprint = {1712.01864}, timestamp = {Wed, 28 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1712-01864.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/McGrawPAARRASGB16, author = {Ian McGraw and Rohit Prabhavalkar and Raziel Alvarez and Montse Gonzalez Arenas and Kanishka Rao and David Rybach and Ouais Alsharif and Hasim Sak and Alexander Gruenstein and Fran{\c{c}}oise Beaufays and Carolina Parada}, title = {Personalized speech recognition on mobile devices}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {5955--5959}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7472820}, doi = {10.1109/ICASSP.2016.7472820}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/McGrawPAARRASGB16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/McGrawPAARRASGB16, author = {Ian McGraw and Rohit Prabhavalkar and Raziel Alvarez and Montse Gonzalez Arenas and Kanishka Rao and David Rybach and Ouais Alsharif and Hasim Sak and Alexander Gruenstein and Fran{\c{c}}oise Beaufays and Carolina Parada}, title = {Personalized Speech recognition on mobile devices}, journal = {CoRR}, volume = {abs/1603.03185}, year = {2016}, url = {http://arxiv.org/abs/1603.03185}, eprinttype = {arXiv}, eprint = {1603.03185}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/McGrawPAARRASGB16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/SiohanR15, author = {Olivier Siohan and David Rybach}, title = {Multitask learning and system combination for automatic speech recognition}, booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015}, pages = {589--595}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ASRU.2015.7404849}, doi = {10.1109/ASRU.2015.7404849}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/asru/SiohanR15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/AleksicGMAHRRM15, author = {Petar S. Aleksic and Mohammadreza Ghodsi and Assaf Hurwitz Michaely and Cyril Allauzen and Keith B. Hall and Brian Roark and David Rybach and Pedro J. Moreno}, title = {Bringing contextual information to google speech recognition}, booktitle = {16th Annual Conference of the International Speech Communication Association, {INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015}, pages = {468--472}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-177}, doi = {10.21437/INTERSPEECH.2015-177}, timestamp = {Tue, 11 Jun 2024 16:45:43 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/AleksicGMAHRRM15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HallCABCNRRRZ15, author = {Keith B. Hall and Eunjoon Cho and Cyril Allauzen and Fran{\c{c}}oise Beaufays and Noah Coccaro and Kaisuke Nakajima and Michael Riley and Brian Roark and David Rybach and Linda Zhang}, title = {Composition-based on-the-fly rescoring for salient n-gram biasing}, booktitle = {16th Annual Conference of the International Speech Communication Association, {INTERSPEECH} 2015, Dresden, Germany, September 6-10, 2015}, pages = {1418--1422}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-340}, doi = {10.21437/INTERSPEECH.2015-340}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HallCABCNRRRZ15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@phdthesis{DBLP:phd/dnb/Rybach14, author = {David Rybach}, title = {Investigations on search methods for speech recognition using weighted finite-state transducers}, school = {{RWTH} Aachen University}, year = {2014}, url = {http://darwin.bth.rwth-aachen.de/opus3/volltexte/2014/5052}, urn = {urn:nbn:de:hbz:82-opus-50526}, timestamp = {Sat, 17 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/phd/dnb/Rybach14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/csl/RybachRA14, author = {David Rybach and Michael Riley and Chris Alberti}, title = {Direct construction of compact context-dependency transducers from data}, journal = {Comput. Speech Lang.}, volume = {28}, number = {1}, pages = {177--191}, year = {2014}, url = {https://doi.org/10.1016/j.csl.2013.04.006}, doi = {10.1016/J.CSL.2013.04.006}, timestamp = {Thu, 20 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/csl/RybachRA14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/BacchianiR14, author = {Michiel Bacchiani and David Rybach}, title = {Context dependent state tying for speech recognition using deep neural network acoustic models}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014}, pages = {230--234}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICASSP.2014.6853592}, doi = {10.1109/ICASSP.2014.6853592}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/BacchianiR14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/RybachNS13, author = {David Rybach and Hermann Ney and Ralf Schl{\"{u}}ter}, title = {Lexical Prefix Tree and {WFST:} {A} Comparison of Two Dynamic Search Concepts for {LVCSR}}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {21}, number = {6}, pages = {1295--1307}, year = {2013}, url = {https://doi.org/10.1109/TASL.2013.2248723}, doi = {10.1109/TASL.2013.2248723}, timestamp = {Sun, 17 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/RybachNS13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/KozielskiRHSN13, author = {Michal Kozielski and David Rybach and Stefan Hahn and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {Open vocabulary handwriting recognition using combined word-level and character-level language models}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013}, pages = {8257--8261}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ICASSP.2013.6639275}, doi = {10.1109/ICASSP.2013.6639275}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/KozielskiRHSN13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/HoffmeisterHRSN12, author = {Bj{\"{o}}rn Hoffmeister and Georg Heigold and David Rybach and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {{WFST} Enabled Solutions to {ASR} Problems: Beyond {HMM} Decoding}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {20}, number = {2}, pages = {551--564}, year = {2012}, url = {https://doi.org/10.1109/TASL.2011.2162402}, doi = {10.1109/TASL.2011.2162402}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/HoffmeisterHRSN12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/RybachSN12, author = {David Rybach and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {Silence is golden: Modeling non-speech events in WFST-based dynamic network decoders}, booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012}, pages = {4205--4208}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ICASSP.2012.6288846}, doi = {10.1109/ICASSP.2012.6288846}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/RybachSN12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/NoldenRSN12, author = {David Nolden and David Rybach and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {Joining advantages of word-conditioned and token-passing decoding}, booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012}, pages = {4425--4428}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ICASSP.2012.6288901}, doi = {10.1109/ICASSP.2012.6288901}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/NoldenRSN12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ShaikRHSN12, author = {M. Ali Basha Shaik and David Rybach and Stefan Hahn and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {Hierarchical hybrid language models for open vocabulary continuous speech recognition using {WFST}}, booktitle = {{ISCA} Workshop on Statistical And Perceptual Audition, {SAPA} 2012, Portland, OR, USA, September 7-8, 2012}, pages = {46--51}, publisher = {{ISCA}}, year = {2012}, url = {https://www.isca-archive.org/sapa\_2012/bashashaik12\_sapa.html}, timestamp = {Thu, 01 Aug 2024 17:01:46 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ShaikRHSN12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/RybachSN11, author = {David Rybach and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {A comparative analysis of dynamic network decoding}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress Center, Prague, Czech Republic}, pages = {5184--5187}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/ICASSP.2011.5947525}, doi = {10.1109/ICASSP.2011.5947525}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/RybachSN11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/RybachR10, author = {David Rybach and Michael Riley}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {Direct construction of compact context-dependency transducers from data}, booktitle = {11th Annual Conference of the International Speech Communication Association, {INTERSPEECH} 2010, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {218--221}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-89}, doi = {10.21437/INTERSPEECH.2010-89}, timestamp = {Tue, 11 Jun 2024 16:45:43 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/RybachR10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/PariharSRH10, author = {Naveen Parihar and Ralf Schl{\"{u}}ter and David Rybach and Eric A. Hansen}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {Parallel lexical-tree based {LVCSR} on multi-core processors}, booktitle = {11th Annual Conference of the International Speech Communication Association, {INTERSPEECH} 2010, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {1485--1488}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-435}, doi = {10.21437/INTERSPEECH.2010-435}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/PariharSRH10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/RybachGSN09, author = {David Rybach and Christian Gollan and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {Audio segmentation for speech recognition using segment features}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan}, pages = {4197--4200}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ICASSP.2009.4960554}, doi = {10.1109/ICASSP.2009.4960554}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/RybachGSN09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icdar/DreuwRGN09, author = {Philippe Dreuw and David Rybach and Christian Gollan and Hermann Ney}, title = {Writer Adaptive Training and Writing Variant Model Refinement for Offline Arabic Handwriting Recognition}, booktitle = {10th International Conference on Document Analysis and Recognition, {ICDAR} 2009, Barcelona, Spain, 26-29 July 2009}, pages = {21--25}, publisher = {{IEEE} Computer Society}, year = {2009}, url = {https://doi.org/10.1109/ICDAR.2009.9}, doi = {10.1109/ICDAR.2009.9}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icdar/DreuwRGN09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HeigoldRSN09, author = {Georg Heigold and David Rybach and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {Investigations on convex optimization using log-linear HMMs for digit string recognition}, booktitle = {10th Annual Conference of the International Speech Communication Association, {INTERSPEECH} 2009, Brighton, United Kingdom, September 6-10, 2009}, pages = {216--219}, publisher = {{ISCA}}, year = {2009}, url = {https://doi.org/10.21437/Interspeech.2009-79}, doi = {10.21437/INTERSPEECH.2009-79}, timestamp = {Tue, 11 Jun 2024 16:45:43 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HeigoldRSN09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/RybachGHHLSN09, author = {David Rybach and Christian Gollan and Georg Heigold and Bj{\"{o}}rn Hoffmeister and Jonas L{\"{o}}{\"{o}}f and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {The {RWTH} aachen university open source speech recognition system}, booktitle = {10th Annual Conference of the International Speech Communication Association, {INTERSPEECH} 2009, Brighton, United Kingdom, September 6-10, 2009}, pages = {2111--2114}, publisher = {{ISCA}}, year = {2009}, url = {https://doi.org/10.21437/Interspeech.2009-604}, doi = {10.21437/INTERSPEECH.2009-604}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/RybachGHHLSN09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/El-DesokyGRSN09, author = {Amr El{-}Desoky and Christian Gollan and David Rybach and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {Investigating the use of morphological decomposition and diacritization for improving Arabic {LVCSR}}, booktitle = {10th Annual Conference of the International Speech Communication Association, {INTERSPEECH} 2009, Brighton, United Kingdom, September 6-10, 2009}, pages = {2679--2682}, publisher = {{ISCA}}, year = {2009}, url = {https://doi.org/10.21437/Interspeech.2009-123}, doi = {10.21437/INTERSPEECH.2009-123}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/El-DesokyGRSN09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/PariharSRH09, author = {Naveen Parihar and Ralf Schl{\"{u}}ter and David Rybach and Eric A. Hansen}, title = {Parallel fast likelihood computation for {LVCSR} using mixture decomposition}, booktitle = {10th Annual Conference of the International Speech Communication Association, {INTERSPEECH} 2009, Brighton, United Kingdom, September 6-10, 2009}, pages = {3047--3050}, publisher = {{ISCA}}, year = {2009}, url = {https://doi.org/10.21437/Interspeech.2009-565}, doi = {10.21437/INTERSPEECH.2009-565}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/PariharSRH09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/tsd/SchulzFR09, author = {Henrik Schulz and Jos{\'{e}} A. R. Fonollosa and David Rybach}, editor = {V{\'{a}}clav Matousek and Pavel Mautner}, title = {Transcription of Catalan Broadcast Conversation}, booktitle = {Text, Speech and Dialogue, 12th International Conference, {TSD} 2009, Pilsen, Czech Republic, September 13-17, 2009. Proceedings}, series = {Lecture Notes in Computer Science}, volume = {5729}, pages = {154--161}, publisher = {Springer}, year = {2009}, url = {https://doi.org/10.1007/978-3-642-04208-9\_24}, doi = {10.1007/978-3-642-04208-9\_24}, timestamp = {Sun, 12 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/tsd/SchulzFR09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/VergyriMWSZGRGSKFM08, author = {Dimitra Vergyri and Arindam Mandal and Wen Wang and Andreas Stolcke and Jing Zheng and Martin Graciarena and David Rybach and Christian Gollan and Ralf Schl{\"{u}}ter and Katrin Kirchhoff and Arlo Faria and Nelson Morgan}, title = {Development of the SRI/nightingale Arabic {ASR} system}, booktitle = {9th Annual Conference of the International Speech Communication Association, {INTERSPEECH} 2008, Brisbane, Australia, September 22-26, 2008}, pages = {1437--1440}, publisher = {{ISCA}}, year = {2008}, url = {https://doi.org/10.21437/Interspeech.2008-415}, doi = {10.21437/INTERSPEECH.2008-415}, timestamp = {Mon, 09 Sep 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/VergyriMWSZGRGSKFM08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/RybachHGSN07, author = {David Rybach and Stefan Hahn and Christian Gollan and Ralf Schl{\"{u}}ter and Hermann Ney}, editor = {Sadaoki Furui and Tatsuya Kawahara}, title = {Advances in Arabic broadcast news transcription at {RWTH}}, booktitle = {{IEEE} Workshop on Automatic Speech Recognition {\&} Understanding, {ASRU} 2007, Kyoto, Japan, December 9-13, 2007}, pages = {449--454}, publisher = {{IEEE}}, year = {2007}, url = {https://doi.org/10.1109/ASRU.2007.4430154}, doi = {10.1109/ASRU.2007.4430154}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/asru/RybachHGSN07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LoofGHHHPRSN07, author = {Jonas L{\"{o}}{\"{o}}f and Christian Gollan and Stefan Hahn and Georg Heigold and Bj{\"{o}}rn Hoffmeister and Christian Plahl and David Rybach and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {The {RWTH} 2007 {TC-STAR} evaluation system for european English and Spanish}, booktitle = {8th Annual Conference of the International Speech Communication Association, {INTERSPEECH} 2007, Antwerp, Belgium, August 27-31, 2007}, pages = {2145--2148}, publisher = {{ISCA}}, year = {2007}, url = {https://doi.org/10.21437/Interspeech.2007-579}, doi = {10.21437/INTERSPEECH.2007-579}, timestamp = {Tue, 11 Jun 2024 16:45:43 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LoofGHHHPRSN07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DreuwRDZN07, author = {Philippe Dreuw and David Rybach and Thomas Deselaers and Morteza Zahedi and Hermann Ney}, title = {Speech recognition techniques for a sign language recognition system}, booktitle = {8th Annual Conference of the International Speech Communication Association, {INTERSPEECH} 2007, Antwerp, Belgium, August 27-31, 2007}, pages = {2513--2516}, publisher = {{ISCA}}, year = {2007}, url = {https://doi.org/10.21437/Interspeech.2007-668}, doi = {10.21437/INTERSPEECH.2007-668}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DreuwRDZN07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/bmvc/ZahediDRDN06, author = {Morteza Zahedi and Philippe Dreuw and David Rybach and Thomas Deselaers and Hermann Ney}, editor = {Mike J. Chantler and Robert B. Fisher and Emanuele Trucco}, title = {Geometric Features for Improving Continuous Appearance-based Sign Language Recognition}, booktitle = {Proceedings of the British Machine Vision Conference 2006, Edinburgh, UK, September 4-7, 2006}, pages = {1019--1028}, publisher = {British Machine Vision Association}, year = {2006}, url = {https://doi.org/10.5244/C.20.104}, doi = {10.5244/C.20.104}, timestamp = {Wed, 03 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/bmvc/ZahediDRDN06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/fgr/DreuwDRKN06, author = {Philippe Dreuw and Thomas Deselaers and David Rybach and Daniel Keysers and Hermann Ney}, title = {Tracking Using Dynamic Programming for Appearance-Based Sign Language Recognition}, booktitle = {Seventh {IEEE} International Conference on Automatic Face and Gesture Recognition {(FGR} 2006), 10-12 April 2006, Southampton, {UK}}, pages = {293--298}, publisher = {{IEEE} Computer Society}, year = {2006}, url = {https://doi.org/10.1109/FGR.2006.107}, doi = {10.1109/FGR.2006.107}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/fgr/DreuwDRKN06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/informatiktage/RybachKN05, author = {David Rybach and Daniel Keysers and Hermann Ney}, title = {Erweiterung eines holistischen statistischen Bilderkenners zur Verwendung von mehreren Merkmalen}, booktitle = {Informatiktage 2005 - Fachwissenschaftlicher Informatik-Kongress, 8. und 9. April 2005, Schloss Birlinghoven, St. Augustin bei Bonn}, series = {{LNI}}, volume = {{S-2}}, pages = {155--158}, publisher = {{GI}}, year = {2005}, timestamp = {Mon, 20 Dec 2021 16:59:24 +0100}, biburl = {https://dblp.org/rec/conf/informatiktage/RybachKN05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.