{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T22:37:05Z","timestamp":1725748625853},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053510","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7039-7043","source":"Crossref","is-referenced-by-count":2,"title":["An Attention-Based Joint Acoustic and Text on-Device End-To-End Model"],"prefix":"10.1109","author":[{"given":"Tara N.","family":"Sainath","sequence":"first","affiliation":[]},{"given":"Ruoming","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Ron J.","family":"Weiss","sequence":"additional","affiliation":[]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[]},{"given":"Chung-cheng","family":"Chiu","sequence":"additional","affiliation":[]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","year":"2019","author":"shen","key":"ref31"},{"article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","year":"2015","author":"abadi","key":"ref30"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards Better Decoding and Language Model Integration in Sequence to Sequence Models","author":"chorowski","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref11","article-title":"Cold fusion: Training seq2seq models together with language models","author":"sriram","year":"2017","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1554"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682172"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683307"},{"key":"ref18","first-page":"5410","article-title":"Almost unsupervised text to speech and automatic speech recognition","author":"ren","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning ICML 2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","year":"2017","author":"van den oord","key":"ref28"},{"key":"ref4","article-title":"Speech recognition with deep neural networks","author":"graves","year":"2012","journal-title":"Proc ICASSP"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref3","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref6","article-title":"Listen, attend and spell","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref29","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref5","first-page":"193","article-title":"Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer","author":"rao","year":"2017","journal-title":"Proc ASRU"},{"key":"ref8","article-title":"Monotonic chunkwise alignments","author":"chiu","year":"2017","journal-title":"Proc ICLR"},{"key":"ref7","first-page":"4835","article-title":"Joint CTC-attention based end-to-end speech recognition using multi-task learning","author":"kim","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2456"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462201"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards Better Decoding and Language Model Integration in Sequence to Sequence Models","author":"chorowski","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generated of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home","author":"kim","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053510.pdf?arnumber=9053510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:09:23Z","timestamp":1656374963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053510\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053510","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}