{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:55:17Z","timestamp":1776884117740,"version":"3.51.2"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462180","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"4919-4923","source":"Crossref","is-referenced-by-count":38,"title":["An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech"],"prefix":"10.1109","author":[{"given":"Hiroshi","family":"Seki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan Le","family":"Roux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John R.","family":"Hershey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Language independent end-to-end architecture for joint language identification and speech recognition","author":"watanabetakaaki hori","year":"2017","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref11","year":"0","journal-title":"VoxForge"},{"key":"ref12","first-page":"4666","article-title":"A longitudinal bilingual Frisian-Dutch radio broadcast database designed for code-switching research","author":"yilmaz","year":"2016","journal-title":"Language Resources and Evaluation Conference"},{"key":"ref13","article-title":"CSR-II (wsj1) complete","volume":"ldc94s13a","year":"1994","journal-title":"Linguistic Data Consortium Philadelphia"},{"key":"ref14","article-title":"CSR-I (wsj0) complete","volume":"ldc93s6a","author":"garofalo","year":"2007","journal-title":"Linguistic Data Consortium Philadelphia"},{"key":"ref15","first-page":"947","article-title":"Spontaneous speech corpus of Japanese","volume":"2","author":"maekawa","year":"2000","journal-title":"International Conference on Language Resources and Evaluation (LREC)"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1007\/11939993_73","article-title":"HKUST\/MTS: A very large scale Mandarin telephone speech corpus","author":"liu","year":"2006","journal-title":"Chinese Spoken Language Processing"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854049"},{"key":"ref19","article-title":"Chainer: a next-generation open source framework for deep learning","author":"tokui","year":"2015","journal-title":"Proceedings of Workshop on Machine Learning Systems (LearningSys) in NIPS"},{"key":"ref4","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"949","DOI":"10.21437\/Interspeech.2017-1296","article-title":"Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM","author":"hori","year":"2017","journal-title":"InterSpeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855129"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.07.008"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2014.2364559"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424246"},{"key":"ref2","article-title":"Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","author":"soltau","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref9","first-page":"229","article-title":"Multilingual speech-to-speech translation system: Voicetra","volume":"2","author":"matsuda","year":"2013","journal-title":"IEEE International Conference on Mobile Data Management (MDM)"}],"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\/08462180.pdf?arnumber=8462180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T20:52:05Z","timestamp":1598215925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462180","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}