{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T04:39:22Z","timestamp":1723264762571},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2013,10,1]],"date-time":"2013-10-01T00:00:00Z","timestamp":1380585600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2013,10]]},"DOI":"10.1109\/tasl.2013.2263803","type":"journal-article","created":{"date-parts":[[2013,6,7]],"date-time":"2013-06-07T18:01:36Z","timestamp":1370628096000},"page":"2006-2014","source":"Crossref","is-referenced-by-count":7,"title":["An Experimental Analysis on Integrating Multi-Stream Spectro-Temporal, Cepstral and Pitch Information for Mandarin Speech Recognition"],"prefix":"10.1109","volume":"21","author":[{"given":"Yow-Bang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shang-Wen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin-shan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-609","article-title":"Improved tonal language speech recognition by integrating spectro-temporal evidence and pitch information with properly chosen tonal acoustic units","author":"li","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947528"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-372","article-title":"Improved tone modeling for Mandarin broadcast news speech recognition","author":"lei","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-32","article-title":"A multi-space distribution (MSD) approach to speech recognition of tonal languages","author":"wang","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-383","article-title":"A comparative large scale study of MLP features for Mandarin ASR","author":"valente","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref30","first-page":"490","article-title":"Building a highly accurate Mandarin speech recognizer","author":"hwang","year":"2007","journal-title":"Proc ASRU"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-370","article-title":"Improved phoneme recognition by integrating evidence from spectro-temporal and cepstral features","author":"li","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495129"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367000"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/11939993_47"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1220","DOI":"10.1152\/jn.2001.85.3.1220","article-title":"Spectro-temporal response field characterization with dynamic ripples in ferret primary auditory cortex","volume":"85","author":"depireux","year":"2001","journal-title":"J Neurophysiol"},{"key":"ref40","year":"0","journal-title":"The Snack Sound Toolkit"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2008.2002708"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495668"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518635"},{"key":"ref14","first-page":"16","article-title":"Improving word accuracy with Gabor feature extraction","volume":"5","author":"kleinschmidt","year":"2002","journal-title":"Proc ICSLP"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-209","article-title":"Multi-stream spectro-temporal features for robust speech recognition","author":"zhao","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-704","article-title":"Complementarity of MFCC, PLP and Gabor features in the presence of speech-intrinsic variabilities","author":"meyer","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.428100"},{"key":"ref18","author":"gelbart","year":"2008","journal-title":"Ensemble feature selection for multi-stream automatic speech recognition"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-747","article-title":"Multi-stream to many-stream: Using spectro-temporal features for ASR","author":"zhao","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-134","article-title":"Incorporating tone-related MLP posteriors in the feature representation for Mandarin ASR","author":"lei","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518572"},{"key":"ref27","first-page":"4549","article-title":"Exploiting prosodic and lexical features for tone modeling in a conditional random field framework","author":"wei","year":"2008","journal-title":"Proc ICASSP"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660023"},{"key":"ref29","article-title":"Advances in Mandarin broadcast speech recognition","author":"hwang","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-692","article-title":"Improved MLP structures for data-driven feature extraction for ASR","author":"zhu","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518713"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518547"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-184","article-title":"Multi-resolution RASTA filtering for tandem-based ASR","author":"hermansky","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-447","article-title":"Data-driven clustered hierarchical tandem system for LVCSR","author":"chang","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref46","year":"0","journal-title":"SRILM?the SRI Language Modeling Toolkit"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-120","article-title":"A multistream multiresolution framework for phoneme recognition","author":"mesgarani","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1987.1165125"},{"key":"ref48","year":"0","journal-title":"Chinese Electronic Dictionary?The Association for Computational Linguistics and Chinese Language Processing"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/89.222876"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/278459.258534"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-371","article-title":"Using spectro-temporal features to improve AFE feature extraction for ASR","author":"ravuri","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947447"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1109\/79.595570","article-title":"Voice dictation of Mandarin Chinese","volume":"14","author":"lee","year":"1997","journal-title":"IEEE Signal Process Mag"},{"key":"ref41","year":"0","journal-title":"MATBN (Mandarin Across Taiwan-Broadcast News) corpus"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/89.554782"},{"key":"ref44","year":"0","journal-title":"Chinese Gigaword"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-346","article-title":"Improved large vocabulary Mandarin speech recognition by selectively using tone information with a two-stage prosodic model","author":"cheng","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"777","DOI":"10.21437\/Interspeech.2011-176","article-title":"Word boundary modelling and full covariance Gaussians for Arabic speech-to-text systems","author":"diehl","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/595576.595581"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376\/6565391\/06527312.pdf?arnumber=6527312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,24]],"date-time":"2022-02-24T12:34:33Z","timestamp":1645706073000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6527312\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,10]]},"references-count":48,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2013.2263803","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,10]]}}}