{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T21:58:32Z","timestamp":1765231112937,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462366","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5864-5868","source":"Crossref","is-referenced-by-count":21,"title":["Improving the Performance of Online Neural Transducer Models"],"prefix":"10.1109","author":[{"given":"Tara N.","family":"Sainath","sequence":"first","affiliation":[]},{"given":"Chung-Cheng","family":"Chiu","sequence":"additional","affiliation":[]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[]},{"given":"Anjuli","family":"Kannan","sequence":"additional","affiliation":[]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Patrick","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"ZhiJeng","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref11","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":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref14","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","volume":"abs 1609 8144","author":"wu","year":"2016","journal-title":"CoRR"},{"key":"ref15","article-title":"Latent Sequence Decompositions","author":"chan","year":"2017","journal-title":"ICLRE"},{"key":"ref16","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":"ref17","article-title":"Cold fusion: Training seq2seq models together with language models","volume":"abs 1708 6426","author":"sriram","year":"2017","journal-title":"CoRR"},{"key":"ref18","article-title":"An analysis of incorporating an external language model into a sequence-to-sequence model","author":"kannan","year":"2018","journal-title":"Submitted to ICASSP"},{"key":"ref19","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":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-232","article-title":"An Analysis of“ Attention” in Sequence-to-Sequence Models,” in Proc. Interspeech","author":"prabhavalkar","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref27","article-title":"State-of-the-art speech recognition with sequence-to-sequence models","author":"chen","year":"2018","journal-title":"submitted to Proc ICA SSP"},{"key":"ref3","article-title":"An Online Sequence-to-sequence Model Using Partial Conditioning","author":"jaitly","year":"2016","journal-title":"Proc NIPS"},{"key":"ref6","article-title":"Con-nectionist Temporal Classification: Labeling Unsegmented Se-quenece Data with Recurrent Neural Networks","author":"graves","year":"2006","journal-title":"Proc ICML"},{"key":"ref5","article-title":"A comparison of Sequence-to-sequence Models for Speech Recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc INTERSPEECH"},{"journal-title":"Improved End-of-Ouerv Detection for Streamino Sneech Recocnition","year":"0","author":"shannon","key":"ref8"},{"key":"ref7","article-title":"Sequence transduction with recurrent neural networks","volume":"abs 1211 3711","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref2","article-title":"Listen, attend and spell","volume":"abs 1508 1211","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref9","article-title":"Exploring Neural Transducers for End-to-End Speech Recognition","author":"battenberg","year":"2017","journal-title":"Proc ASRU"},{"key":"ref1","article-title":"Attention-Based Models for Speech Recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref20","article-title":"Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition","author":"sak","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref22","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","volume":"abs 1409 473","author":"bahdanau","year":"2014","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proceedings of ICL"},{"key":"ref23","article-title":"Large Scale Distributed Deep Networks","author":"dean","year":"2012","journal-title":"Proc NIPS"},{"key":"ref26","article-title":"Attention Is All You Need","volume":"abs 1706 3762","author":"vaswani","year":"2017","journal-title":"CoRR"},{"journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems","year":"2015","author":"abadi","key":"ref25"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462366.pdf?arnumber=8462366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:17:47Z","timestamp":1598231867000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462366\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462366","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}