{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:35:20Z","timestamp":1730230520383,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683868","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6530-6534","source":"Crossref","is-referenced-by-count":12,"title":["Learned in Speech Recognition: Contextual Acoustic Word Embeddings"],"prefix":"10.1109","author":[{"given":"Shruti","family":"Palaskar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vikas","family":"Raunak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Investigation of Recurrent-Neural-Network Architectures and Learning Methods for Spoken Language Understanding","year":"2013","author":"mesnil","key":"ref30"},{"key":"ref10","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref12","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639664"},{"article-title":"Very deep convo-lutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"article-title":"Neural speech recognizer: Acoustic-to-word lstm model for large vocabulary speech recognition","year":"2016","author":"soltau","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462017"},{"article-title":"State-of-the-art speech recognition with sequence-to-sequence models","year":"2017","author":"chiu","key":"ref18"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1109\/ASRU.2017.8268935","article-title":"Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer","author":"rao","year":"2017","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref28","article-title":"How2: A large-scale dataset for multimodal language understanding","author":"sanabria","year":"2018","journal-title":"Submitted to Visually Grounded Interaction and Language (ViGIL) NIPS 2018 Workshop"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"article-title":"Senteval: An evaluation toolkit for universal sentence representations","year":"2018","author":"conneau","key":"ref27"},{"key":"ref3","first-page":"6294","article-title":"Learned in translation: Contextualized word vectors","author":"mccann","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472619"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/116580.116612"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2341"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404800"},{"key":"ref7","article-title":"Word embeddings for speech recognition","author":"bengio","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"article-title":"Multi-view recurrent neural acoustic word embeddings","year":"2016","author":"he","key":"ref9"},{"key":"ref1","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"article-title":"Building competitive direct acoustics-to-word models for english conversational speech recognition","year":"2017","author":"audhkhasi","key":"ref22"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1109\/ICASSP.1992.225858","article-title":"Switchboard: Telephone speech corpus for research and development","volume":"1","author":"godfrey","year":"1992","journal-title":"Acoustics Speech and Signal Processing 1992 ICASSP-92 1992 IEEE International Conference on"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"journal-title":"Acoustic-to-word attention-based model complemented with character-level ctc-based model","year":"0","author":"ueno","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461361"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683868.pdf?arnumber=8683868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:14:21Z","timestamp":1657854861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683868\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683868","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}