{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T12:56:28Z","timestamp":1752670588568},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639563","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"212-218","source":"Crossref","is-referenced-by-count":4,"title":["Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR"],"prefix":"10.1109","author":[{"given":"Hirofumi","family":"Inaguma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masato","family":"Mimura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinsuke","family":"Sakai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","article-title":"Corpus of spontaneous japanese: Its design and evaluation","author":"maekawa","year":"2003","journal-title":"ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref32","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proceeding NIPS"},{"key":"ref31","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"Proc of ICML"},{"key":"ref30","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv preprint arXiv 1609 09861"},{"article-title":"Automatic differentiation in pytorch","year":"2017","author":"paszke","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2025"},{"key":"ref35","article-title":"Tying word vectors and word classifiers: A loss framework for language modeling","author":"inan","year":"2016","journal-title":"arXiv preprint arXiv 1611 01462"},{"key":"ref34","first-page":"279","article-title":"Empirical exploration of novel architectures and objectives for language models","author":"kurata","year":"2017","journal-title":"Proc of Inter-speech"},{"key":"ref10","first-page":"939","article-title":"A comparison of sequence-to-sequence models for speech recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc of Inter-speech"},{"key":"ref11","first-page":"206","article-title":"Exploring neural transducers for end-to-end speech recognition","author":"battenberg","year":"2017","journal-title":"Proc of ASRU"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462576"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref14","first-page":"1468","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"Proc of Interspeech"},{"key":"ref15","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 of Interspeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461935"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"3707","DOI":"10.21437\/Interspeech.2017-1566","article-title":"Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary recognition","author":"soltau","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref18","first-page":"111","article-title":"Acoustic-to-word model without OOV","author":"li","year":"2017","journal-title":"Proc of ASRU"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"523","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 of Interspeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref6","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2015","journal-title":"arXiv preprint arXiv 1512 00327"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proceedings of ICL"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc of NIPS"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"137","DOI":"10.21437\/Interspeech.2017-1544","article-title":"Comparing human and machine errors in conversational speech transcription","author":"stolcke","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"132","DOI":"10.21437\/Interspeech.2017-405","article-title":"English conversational telephone speech recognition by humans and machines","author":"saon","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","first-page":"5824","article-title":"An analysis of incorporating an external language model into a sequence-to-sequence model","author":"kannan","year":"2017","journal-title":"Proc of ICASSP"},{"key":"ref24","first-page":"2438","article-title":"Analyzing hidden representations in end-to-end automatic speech recognition systems","author":"belinkov","year":"2017","journal-title":"Proc of NIPS"},{"key":"ref23","first-page":"3532","article-title":"Multitask learning with low-level auxiliary tasks for encoder-decoder based speech recognition","author":"toshniwal","year":"2017","journal-title":"Proc of Inter-speech"},{"key":"ref26","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc of ASRU"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2018,12,18]]},"location":"Athens, Greece","end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639563.pdf?arnumber=8639563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T05:37:50Z","timestamp":1643261870000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639563","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}