{"id":"https://openalex.org/W2126940615","doi":"https://doi.org/10.1109/tasl.2008.2005347","title":"Unsupervised Adaptation of Categorical Prosody Models for Prosody Labeling and Speech Recognition","display_name":"Unsupervised Adaptation of Categorical Prosody Models for Prosody Labeling and Speech Recognition","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2126940615","doi":"https://doi.org/10.1109/tasl.2008.2005347","mag":"2126940615","pmid":"https://pubmed.ncbi.nlm.nih.gov/19763253"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2008.2005347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2005347","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090325019","display_name":"Sankaranarayanan Ananthakrishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S. Ananthakrishnan","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA 90089 USA. He is now with BBN Technologies, Cambridge, MA 02138 USA (e-mail: shankar.ananthakrishnan@gmail.com )","Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","BBN Technologies, GTE, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA 90089 USA. He is now with BBN Technologies, Cambridge, MA 02138 USA (e-mail: shankar.ananthakrishnan@gmail.com )","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010767866","display_name":"S. Narayanan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Narayanan","raw_affiliation_strings":["BBN Technol., Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"BBN Technol., Cambridge, MA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090325019"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":3.1708,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.9240672,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"17","issue":"1","first_page":"138","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.9261986017227173},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7555135488510132},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6710795760154724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6318960189819336},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6024864912033081},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5090715289115906},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.49091631174087524},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.45975637435913086},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45635560154914856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45541146397590637},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.44345542788505554},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18139347434043884},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15182554721832275},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.06756746768951416}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9261986017227173},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7555135488510132},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6710795760154724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6318960189819336},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6024864912033081},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5090715289115906},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.49091631174087524},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.45975637435913086},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45635560154914856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45541146397590637},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.44345542788505554},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18139347434043884},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15182554721832275},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.06756746768951416},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2008.2005347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2005347","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmid:19763253","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19763253","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on audio, speech, and language processing","raw_type":null},{"id":"pmh:oai:europepmc.org:2008662","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2745178","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W3745469","https://openalex.org/W26118603","https://openalex.org/W88081813","https://openalex.org/W139005550","https://openalex.org/W154023371","https://openalex.org/W1486632395","https://openalex.org/W1597422500","https://openalex.org/W1631260214","https://openalex.org/W1977021391","https://openalex.org/W1979679014","https://openalex.org/W2000629566","https://openalex.org/W2008199296","https://openalex.org/W2100969003","https://openalex.org/W2101593422","https://openalex.org/W2106009717","https://openalex.org/W2125689567","https://openalex.org/W2138435742","https://openalex.org/W2156427312","https://openalex.org/W2594610113","https://openalex.org/W3088321056","https://openalex.org/W3140653788","https://openalex.org/W6601108254","https://openalex.org/W6605654861","https://openalex.org/W6635774499","https://openalex.org/W6676159905"],"related_works":["https://openalex.org/W2071315723","https://openalex.org/W2507083698","https://openalex.org/W2465473908","https://openalex.org/W49590631","https://openalex.org/W2474947928","https://openalex.org/W2370788932","https://openalex.org/W4301230705","https://openalex.org/W2967415048","https://openalex.org/W2150890698","https://openalex.org/W2401394187"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,53],"recognition":[2],"(ASR)":[3],"systems":[4],"rely":[5],"almost":[6],"exclusively":[7],"on":[8,39,189],"short-term":[9],"segment-level":[10],"features":[11],"(MFCCs),":[12],"while":[13,196],"ignoring":[14],"higher":[15],"level":[16],"suprasegmental":[17],"cues":[18],"that":[19,30,148],"are":[20,59],"characteristic":[21],"of":[22,33,70,118,124,158],"human":[23],"speech.":[24],"However,":[25,55],"recent":[26],"experiments":[27,146],"have":[28],"shown":[29],"categorical":[31,56,126,142],"representations":[32],"prosody,":[34],"such":[35],"as":[36,80],"those":[37],"based":[38],"the":[40,68,75,116,119,132,140,149,156,159,162,186,190,197,211],"Tones":[41],"and":[42,64,85,121,166,181],"Break":[43],"Indices":[44],"(ToBI)":[45],"annotation":[46],"standard,":[47],"can":[48],"be":[49],"used":[50],"to":[51,67,185],"enhance":[52],"recognizers.":[54],"prosody":[57,127,143,160],"models":[58,168],"severely":[60],"limited":[61],"in":[62,205],"scope":[63],"coverage":[65],"due":[66],"lack":[69],"large":[71],"corpora":[72],"annotated":[73],"with":[74,102,139],"relevant":[76],"prosodic":[77,164],"symbols":[78],"(such":[79],"pitch":[81,171],"accent,":[82],"word":[83,206],"prominence,":[84],"boundary":[86],"tone":[87],"labels).":[88],"In":[89],"this":[90],"paper,":[91],"we":[92,130],"first":[93],"present":[94],"an":[95],"architecture":[96],"for":[97,113],"augmenting":[98],"a":[99,201],"standard":[100],"ASR":[101,134,137,199],"symbolic":[103],"prosody.":[104],"We":[105],"then":[106],"discuss":[107],"two":[108],"novel,":[109],"un-supervised":[110],"adaptation":[111,152],"techniques":[112,153],"improving,":[114],"respectively,":[115],"quality":[117,157],"linguistic":[120],"acoustic":[122,167],"components":[123],"our":[125],"models.":[128,144],"Finally,":[129],"implement":[131],"augmented":[133],"by":[135,179],"enriching":[136],"lattices":[138],"adapted":[141,163],"Our":[145],"show":[147],"proposed":[150],"unsupervised":[151],"significantly":[154],"improve":[155],"models;":[161],"language":[165],"reduce":[169],"binary":[170],"accent":[172],"(presence":[173],"versus":[174],"absence)":[175],"classification":[176],"error":[177,207],"rate":[178,208],"13.8%":[180],"4.3%,":[182],"respectively":[183],"(relative":[184],"seed":[187],"models)":[188],"Boston":[191],"University":[192],"Radio":[193],"News":[194],"Corpus,":[195],"prosody-enriched":[198],"exhibits":[200],"3.1%":[202],"relative":[203],"reduction":[204],"(WER)":[209],"over":[210],"baseline":[212],"system.":[213]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}