{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:39:46Z","timestamp":1775281186355,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2011,2,1]],"date-time":"2011-02-01T00:00:00Z","timestamp":1296518400000},"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":[[2011,2]]},"DOI":"10.1109\/tasl.2010.2045943","type":"journal-article","created":{"date-parts":[[2010,3,19]],"date-time":"2010-03-19T12:34:01Z","timestamp":1269002041000},"page":"225-241","source":"Crossref","is-referenced-by-count":46,"title":["Analysis of MLP-Based Hierarchical Phoneme Posterior Probability Estimator"],"prefix":"10.1109","volume":"19","author":[{"given":"Joel","family":"Pinto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sivaram","family":"Garimella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathew","family":"Magimai-Doss","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hynek","family":"Hermansky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herv\u00e9","family":"Bourlard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"365","article-title":"mlp based hierarchical system for task adaptation in asr","author":"pinto","year":"2009","journal-title":"Proc IEEE Workshop Autom Speech Recognition Understanding (ASRU)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2007.03.004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT.2000.854165"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/72.279192"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659949"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"2242","DOI":"10.21437\/Interspeech.2008-445","article-title":"on the combination of auditory and modulation frequency channels for asr applications","author":"valente","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1005687"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415275"},{"key":"ref35","first-page":"757","article-title":"probabilistic and bottleneck features for lvcsr of meetings","author":"grezl","year":"2007","journal-title":"Proc IEEE Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref34","author":"abdel-haleem","year":"2006","journal-title":"Conditional random fields for continuous speech recognition"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"361","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596173"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518572"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.879807"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1511826"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518547"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758119"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/3-540-49430-8_2","author":"lecun","year":"1998","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/89.326615"},{"key":"ref23","first-page":"429","article-title":"learning discriminative temporal patterns in speech: development of novel traps-like classifiers","author":"chen","year":"2001","journal-title":"Proc ICSLP"},{"key":"ref26","first-page":"422","article-title":"a new asr approach based on independent processing and recombination of partial frequency bands","author":"bourlard","year":"1996","journal-title":"Proc ICSLP"},{"key":"ref25","author":"fletcher","year":"1995","journal-title":"Speech and hearing in communication"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959958"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1002\/9780471679370"},{"key":"ref58","author":"lehtonen","year":"2005","journal-title":"Hierarchical approach for spotting keywords"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"2414","DOI":"10.21437\/Interspeech.2008-132","article-title":"combining evidence from a generative and a discriminative model in phoneme recognition","author":"pinto","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1005863"},{"key":"ref55","first-page":"517","article-title":"tandem acoustic modeling in large-vocabulary recognition","volume":"1","author":"ellis","year":"2001","journal-title":"Proc IEEE Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2004.1381123"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/89.260334"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/3477.752793"},{"key":"ref10","first-page":"1635","article-title":"tandem connectionist feature extraction for conventional hmm systems","author":"hermansky","year":"2000","journal-title":"Proc IEEE Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref11","author":"aradilla","year":"2008","journal-title":"Acoustic models for posterior features in speech recognition"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/29.46546"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518643"},{"key":"ref13","author":"pinto","year":"2007","journal-title":"Significance of contextual information in phoneme recognition"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1093\/imamci\/1.3.243"},{"key":"ref15","author":"volterra","year":"1930","journal-title":"Theory of Functionals and of Integro-Differential Equations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.759875"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.916057"},{"key":"ref19","first-page":"4049","article-title":"crandem systems: conditional random field acoustic models for hidden markov models","author":"fosler-lussier","year":"2008","journal-title":"Proc IEEE Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1433","DOI":"10.21437\/Interspeech.2008-414","article-title":"transcribing broadcast data using mlp features","author":"fousek","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"921","DOI":"10.21437\/Interspeech.2004-337","article-title":"on using mlp features in lvcsr","author":"zhu","year":"2004","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960620"},{"key":"ref8","author":"ikbal","year":"2004","journal-title":"Nonlinear feature transformations for noise robust speech recognition"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.4.461"},{"key":"ref49","author":"pinto","year":"2008","journal-title":"Volterra series for analyzing MLP based phoneme posterior estimator"},{"key":"ref9","author":"misra","year":"2006","journal-title":"Multi-stream processing for noise robust speech recognition"},{"key":"ref46","year":"0","journal-title":"ICSI Quicknet Software Package"},{"key":"ref45","author":"fitt","year":"2000","journal-title":"Documentation and User Guide to UNISYN Lexicon and Post-Lexical Rules"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1007\/11965152_26","article-title":"juicer: a weighted finite state transducer speech decoder","author":"moore","year":"2006","journal-title":"Proc Mach Learn Multimodal Interaction 2nd Int Workshop Revised Sel Papers"},{"key":"ref47","year":"0","journal-title":"SRILM-The SRI language modeling toolkit"},{"key":"ref42","article-title":"the cu-htk english cts system","author":"woodland","year":"2003","journal-title":"Proc Rich Transcription Workshop"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1325969"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_30"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/5609232\/05432979.pdf?arnumber=5432979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T00:57:50Z","timestamp":1635123470000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5432979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,2]]},"references-count":58,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2010.2045943","relation":{},"ISSN":["1558-7916"],"issn-type":[{"value":"1558-7916","type":"print"}],"subject":[],"published":{"date-parts":[[2011,2]]}}}