{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T23:00:05Z","timestamp":1729638005771,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461935","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"4759-4763","source":"Crossref","is-referenced-by-count":48,"title":["Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition"],"prefix":"10.1109","author":[{"given":"Kartik","family":"Audhkhasi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Saon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Picheny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"crossref","first-page":"1931","DOI":"10.21437\/Interspeech.2009-558","article-title":"Towards using hybrid word and fragment units for vocabulary independent LVCSR systems","author":"rastrow","year":"2009","journal-title":"InterSpeech"},{"key":"ref32","first-page":"277","article-title":"Fast decoding for open vocabulary spoken term detection","author":"ramabhadran","year":"2009","journal-title":"Proc NAACL-HLT"},{"key":"ref31","article-title":"Fast vocabulary-independent audio search using path-based graph indexing","author":"siohan","year":"2005","journal-title":"Proc European Conference on Speech Communication and Technology"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1298","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 2017"},{"key":"ref10","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref12","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1038"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"journal-title":"Latent sequence decompositions","year":"2016","author":"chan","key":"ref15"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1566","article-title":"Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition","author":"soltau","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref17","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"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-405","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref19","first-page":"1532","article-title":"Glove: Global Vectors for Word Representation","volume":"14","author":"pennington","year":"0","journal-title":"proceedings of the 2014 EMNLP"},{"key":"ref28","article-title":"Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling","author":"liu","year":"2017","journal-title":"Proc ICML"},{"key":"ref4","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume":"14","author":"graves","year":"0","journal-title":"Proc of ICML 2014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref6","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"Proc INTERSPEECH"},{"journal-title":"Exploring neural transducers for end-to-end speech recognition","year":"2017","author":"battenberg","key":"ref29"},{"key":"ref5","first-page":"4805","article-title":"Advances in all-neural speech recognition","author":"zweig","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472152"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"journal-title":"Deep speech Scaling up end-to-end speech recognition","year":"2014","author":"hannun","key":"ref9"},{"journal-title":"Statistical Methods for Speech Recognition","year":"1997","author":"jelinek","key":"ref1"},{"journal-title":"PyTorch","year":"0","key":"ref20"},{"key":"ref22","article-title":"Curriculum learning","author":"bengio","year":"0","journal-title":"Proc ICML 2009"},{"key":"ref21","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"journal-title":"Dense prediction on sequences with time-dilated convolutions for speech recognition","year":"2016","author":"sercu","key":"ref26"},{"journal-title":"Achieving human parity in conversational speech recognition","year":"2016","author":"xiong","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\/08461935.pdf?arnumber=8461935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T09:07:55Z","timestamp":1693904875000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461935","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}