{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:09:28Z","timestamp":1784300968753,"version":"3.55.0"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462557","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"1-5","source":"Crossref","is-referenced-by-count":39,"title":["Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition"],"prefix":"10.1109","author":[{"given":"Xuesong","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kartik","family":"Audhkhasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel","family":"Thomas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Improving deep neural networks based multi-accent mandarin speech recognition using i-vectors and accent-specific top layer","author":"chen","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918420"},{"key":"ref12","first-page":"217","article-title":"Accent detection and speech recognition for shanghai-accented mandarin","author":"zheng","year":"2005","journal-title":"InterSpeech"},{"key":"ref13","article-title":"Multi-dialectical languages effect on speech recognition: Too much choice can hurt","author":"mohamed","year":"2015","journal-title":"International Conference on Natural Language and Speech Processing (ICNLSP)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-linguistics-030514-125050"},{"key":"ref15","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning (ICML-14)"},{"key":"ref16","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref17","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"Proceedings of INTER-SPEECH"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref19","author":"hannun","year":"2014","journal-title":"Deep speech Scaling up end-to-end speech recognition"},{"key":"ref28","first-page":"630","article-title":"Generalization and parameter estimation in feedforward nets: Some experiments","volume":"ii","author":"bourlard","year":"1990","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.4324\/9781315833057","author":"holmes","year":"2013","journal-title":"An Introduction to Sociolinguistics"},{"key":"ref27","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/B:IJST.0000017014.52972.1d"},{"key":"ref6","article-title":"Using prosody and phonotactics in arabic dialect identification","author":"biadsy","year":"2009","journal-title":"Tenth Annual Conference of the International Speech Communication Association"},{"key":"ref29","author":"daum\u00e9","year":"2009","journal-title":"Frustratingly Easy Domain Adaptation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472798"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953071"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846328"},{"key":"ref2","author":"saon","year":"0","journal-title":"English conversational telephone speech recognition by humans and machines"},{"key":"ref9","article-title":"Multi-accent deep neural network acoustic model with accent-specific top layer using the kld-regularized model adaptation","author":"huang","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref1","author":"xiong","year":"0","journal-title":"Achieving human parity in conversational speech recognition"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1038"},{"key":"ref22","first-page":"3249","article-title":"A study of the recurrent neural network encoder-decoder for large vocabulary speech recognition","author":"lu","year":"2015","journal-title":"InterSpeech"},{"key":"ref21","author":"chorowski","year":"2014","journal-title":"End-to-end continuous speech recognition using attention-based recurrent nn First results"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref26","first-page":"97","article-title":"The ibm attila speech recognition toolkit","author":"soltau","year":"2010","journal-title":"Spoken Language Technology Work-shop(SLT)"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"959","DOI":"10.21437\/Interspeech.2017-546","article-title":"Direct acoustics-to-word models for English conversational speech recognition","author":"audhkhasi","year":"2017","journal-title":"Proc INTERSPEECH"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"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\/08462557.pdf?arnumber=8462557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T00:56:58Z","timestamp":1598230618000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462557","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}