{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:44:40Z","timestamp":1753602280791,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462017","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5794-5798","source":"Crossref","is-referenced-by-count":58,"title":["Advancing Acoustic-to-Word CTC Model"],"prefix":"10.1109","author":[{"given":"Jinyu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoli","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amit","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1705","article-title":"Recurrent neural aligner: An encoder-decoder neural network model for sequence to sequence mapping","author":"sak","year":"2017","journal-title":"Proc INTERSPEECH"},{"journal-title":"Latent sequence decompositions","year":"2016","author":"chan","key":"ref30"},{"journal-title":"Gram-CTC Automatic unit selection and target decomposition for sequence labelling","year":"2017","author":"liu","key":"ref10"},{"journal-title":"Direct acoustics-to-word models for English conversational speech recognition","year":"2017","author":"audhkhasi","key":"ref11"},{"key":"ref12","article-title":"Acoustic-to-Word Model Without OOV","author":"li","year":"2017","journal-title":"Proc ASRU"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510508"},{"key":"ref14","article-title":"Developing far-field speaker system via teacher-student learning","author":"li","year":"2018","journal-title":"Proc ICASSP"},{"journal-title":"Modelling out-of-vocabulary words for robust speech recognition","year":"2002","author":"bazzi","key":"ref15"},{"key":"ref16","first-page":"1","article-title":"Transcription of out-of-vocabulary words in large vocabulary speech recognition based on phoneme-to-grapheme conversion","volume":"1","author":"decadt","year":"2002","journal-title":"Proc ICASSP"},{"key":"ref17","first-page":"1","article-title":"Hybrid language models for out of vocabulary word detection in large vocabulary conversational speech recognition","volume":"1","author":"yazgan","year":"2004","journal-title":"Proc ICASSP"},{"key":"ref18","first-page":"725","article-title":"Open vocabulary speech recognition with flat hybrid models","author":"bisani","year":"2005","journal-title":"Proc Inter-speech"},{"key":"ref19","article-title":"Building competitive direct acoustics-to-word models for english conversational speech recognition","author":"audhkhasi","year":"2018","journal-title":"Submitted to ICASSP"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref27","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":"ref3","article-title":"Deep Speech: Scaling up End-to-End Speech Recognition","volume":"abs 1412 5567","author":"hannun","year":"2014","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref29","article-title":"State-of-the-art speech recognition with sequence-to-sequence models","author":"chiu","year":"2018","journal-title":"Submitted to ICASSP"},{"key":"ref5","article-title":"Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition","author":"sak","year":"2015","journal-title":"Proc INTERSPEECH"},{"journal-title":"Neural speech recognizer Acoustic-to-word lstm model for large vocabulary speech recognition","year":"0","author":"soltau","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-71"},{"key":"ref2","first-page":"1764","article-title":"Towards End-to-End Speech Recognition with Recurrent Neural Networks","author":"graves","year":"2014","journal-title":"Machine Learning Research"},{"key":"ref9","first-page":"4805","article-title":"Advances in All-Neural Speech Recognition","author":"zweig","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref1","first-page":"369","article-title":"Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks","author":"graves","year":"2006","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref24","article-title":"Advancing connectionist temporal classification with attention modeling","author":"das","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"709","DOI":"10.21437\/Interspeech.2017-505","article-title":"CTC training of multi-phone acoustic models for speech recognition","author":"siohan","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref25","article-title":"Listen, Attend and Spell","volume":"abs 1508 1211","author":"chan","year":"2015","journal-title":"CoRR"}],"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\/08462017.pdf?arnumber=8462017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T04:27:40Z","timestamp":1598243260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462017","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}