{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T19:52:58Z","timestamp":1729626778956,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/apsipa.2015.7415462","type":"proceedings-article","created":{"date-parts":[[2016,3,28]],"date-time":"2016-03-28T15:11:46Z","timestamp":1459177906000},"page":"1194-1197","source":"Crossref","is-referenced-by-count":3,"title":["Integrating prosodic information into recurrent neural network language model for speech recognition"],"prefix":"10.1109","author":[{"given":"Tong","family":"Fu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xihong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.09.003"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-E"},{"key":"ref14","first-page":"518","article-title":"A robust algorithm for pitch tracking (rapt)","volume":"495","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref15","first-page":"749","article-title":"An effective speech preprocessing technique for normalized cross-correlation pitch extractor","author":"nazrul","year":"2003","journal-title":"IEEE ISSPIT"},{"key":"ref16","first-page":"1","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854049"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424228"},{"key":"ref19","article-title":"Statistical language models based on neural networks","author":"mikolov","year":"2012","journal-title":"Presentation at Google Mountain View 2nd April"},{"journal-title":"Prosodic modeling for improved speech recognition and understanding","year":"2001","author":"wang","key":"ref4"},{"key":"ref3","first-page":"147","article-title":"Prosody models for conversational speech recognition","author":"ostendorf","year":"2003","journal-title":"Proc of the 2nd Plenary Meeting and Symposium on Prosody and Speech Processing"},{"key":"ref6","article-title":"Incorporation of prosodic modules for large vocabulary continuous speech recognition","author":"lee","year":"2001","journal-title":"ISCA Tutorial and Research Workshop (ITRW) on Prosody in Speech Recognition and Understanding"},{"key":"ref5","article-title":"Modeling word duration for better speech recognition","author":"gadde","year":"2000","journal-title":"Proceedings of NIST Speech Transcription Workshop"},{"journal-title":"Dynamic Pronunciation Models for Automatic Speech Recognition","year":"1999","author":"fosler-lussier","key":"ref8"},{"key":"ref7","first-page":"941","article-title":"Noise robust speech recognition using f0 contour extracted by hough transform","author":"iwano","year":"2002","journal-title":"ICSLP-2002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.242487"},{"key":"ref9","first-page":"937","article-title":"Statistical language modeling with prosodic boundaries and its use for continuous speech recognition","author":"hirose","year":"2002","journal-title":"InterSpeech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78155-4_17"}],"event":{"name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","start":{"date-parts":[[2015,12,16]]},"location":"Hong Kong","end":{"date-parts":[[2015,12,19]]}},"container-title":["2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7406495\/7415286\/07415462.pdf?arnumber=7415462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T08:18:30Z","timestamp":1655367510000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7415462\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/apsipa.2015.7415462","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}