{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T04:58:52Z","timestamp":1755838732651,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462380","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"5859-5863","source":"Crossref","is-referenced-by-count":26,"title":["No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models"],"prefix":"10.1109","author":[{"given":"Tara N.","family":"Sainath","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shankar","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungji","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anjuli","family":"Kannan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Rybach","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vlad","family":"Schogol","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chung-Cheng","family":"Chiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","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":"ref11","article-title":"A Comparison of Sequence-to-sequence Models for Speech Recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref12","article-title":"Streaming Small-footprint Keyword Spotting Using Sequence-to-Sequence Models","author":"he","year":"2017","journal-title":"Proc ASRU"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_28"},{"key":"ref15","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":"ref16","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":"ref17","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":"ref18","article-title":"Multi-dialect speech recognition with a single sequence-to-sequence model","author":"li","year":"2018","journal-title":"Submitted to ICASSP"},{"key":"ref19","article-title":"Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition","author":"sak","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref4","article-title":"Revisiting graphemes with increasing amounts of data","author":"sung","year":"2008","journal-title":"ICASSP"},{"key":"ref3","first-page":"1145","article-title":"Multilingual acoustic modeling using graphemes","author":"kanthak","year":"2003","journal-title":"Proc of the European Conference On Speech Communication"},{"key":"ref6","article-title":"Multi-accent Speech Recognition with Hierarchical Grapheme Based Models","author":"rao","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref5","article-title":"From speech to letters using a novel neural network architecture for grapheme based ASR","author":"eyben","year":"2009","journal-title":"Automatic Speech Recognition and Understanding ASRU"},{"key":"ref8","article-title":"Listen, attend and spell","volume":"abs 1508 1211","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref7","article-title":"Attention-Based Models for Speech Recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707759"},{"journal-title":"Deep speech 2 End-to-end speech recognition in english and mandarin","year":"2015","author":"amodei","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2226158"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"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":"State-of-the-art speech recognition with sequence-to-sequence models","author":"chen","year":"2018","journal-title":"Submitted to ICASSP"},{"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\/08462380.pdf?arnumber=8462380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T21:18:25Z","timestamp":1598217505000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462380","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}