{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T13:23:09Z","timestamp":1769692989419,"version":"3.49.0"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/apsipa.2014.7041576","type":"proceedings-article","created":{"date-parts":[[2015,2,18]],"date-time":"2015-02-18T00:30:35Z","timestamp":1424219435000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Incorporating tone features to convolutional neural network to improve Mandarin\/Thai speech recognition"],"prefix":"10.1109","author":[{"given":"Xinhui","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masahiro","family":"Saiko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiori","family":"Hori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"1308","article-title":"Pylearn2 a machine learning research library","author":"gooodfellow","year":"2013"},{"key":"ref32","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref31","first-page":"29","article-title":"Multi-lingual speech-to-speech translation system: VoiceTra","author":"matsuda","year":"2013","journal-title":"Proc IEEE 14th International Converence on Mobile Data Management"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2009.5278377"},{"key":"ref10","first-page":"1523","article-title":"Pitch Tracking and Tone Features for Mandarin Speech Recognition","author":"huang","year":"2000","journal-title":"Proc ICASSP"},{"key":"ref11","article-title":"Porting DECIPHER from English to Mandarin","author":"hwang","year":"2004","journal-title":"Proc DARPA 2004 Rich Transcriptions Workshop"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947394"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"2426","DOI":"10.21437\/Interspeech.2008-135","article-title":"Recent Improvement of the RWTH GALE Mandarin LVCSR System","author":"plahl","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref14","first-page":"1077","article-title":"The CU-HTK Mandarin Broadcast AST News Transcriptions","author":"sinha","year":"2006","journal-title":"Proc ICASSP"},{"key":"ref15","first-page":"2613","article-title":"Advances in Mandarin Broadcast Speech Recognition","author":"hwang","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref16","first-page":"1537","article-title":"Progress in the BNN 2007 Mandarin Speech to Text System","author":"ng","year":"2008","journal-title":"Proc ICASSP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163943"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415249"},{"key":"ref19","first-page":"84","article-title":"Incorporating Tone Information To Improve Thai Continuous Speech Recognition","author":"pisarn","year":"2003","journal-title":"Proc on Intelligent Technologies Chiangmai Thailand"},{"key":"ref28","first-page":"90","article-title":"SRILM - An extensible Language Modeling Toolkit","volume":"2","author":"stolcke","year":"2002","journal-title":"Proc ICSLP"},{"key":"ref4","article-title":"Leaning Methods for Generic Object Recognition with Invariance to Pose and Lighting","author":"lecun","year":"2004","journal-title":"Proc CVPR 04 IEEE Press"},{"key":"ref27","year":"0"},{"key":"ref3","first-page":"437","article-title":"Conversational Speech transcription Using Context-dependent Deep Neural Network","author":"li","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.10.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/72.554195"},{"key":"ref8","article-title":"Exploring Convolutional Neural Network Structures and Optimization Techniques for Speech Recognition","author":"hamid","year":"2013","journal-title":"Proc Interspeech ppxx-yy"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1109\/LSP.2014.2325781","article-title":"Convolutional Neural Networks for Distant Speech Recognition","volume":"21","author":"swietojanski","year":"2014","journal-title":"Signal Processing Letters IEEE"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288863"},{"key":"ref20","first-page":"76","article-title":"An HMM-based Method for Thai Spelling Speech Recognition,” Computer & Mathematics with Applications","volume":"54","author":"pisarn","year":"2007"},{"key":"ref22","first-page":"2513","article-title":"A Pitch Extraction Algorithm Tuned for Automatic Speech Recognition","author":"ghahremani","year":"2004","journal-title":"Proc ICASSP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707740"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-221","article-title":"Noise Robust Pitch Tracking by Subband Autocorrelation Classification","author":"lee","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref23","first-page":"495","article-title":"A Robust Algorithm for Pitch Tracking (RAPT)","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref26","year":"0"},{"key":"ref25","first-page":"29","article-title":"The Fundamental Frequency Variation Spectrum","author":"laskowski","year":"2008","journal-title":"Proc 21st Swedish Phonetics Conference (Fonetik 2008)"}],"event":{"name":"2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","location":"Chiang Mai, Thailand","start":{"date-parts":[[2014,12,9]]},"end":{"date-parts":[[2014,12,12]]}},"container-title":["Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7016284\/7041492\/07041576.pdf?arnumber=7041576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,30]],"date-time":"2022-04-30T01:16:00Z","timestamp":1651281360000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7041576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/apsipa.2014.7041576","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}