{"id":"https://openalex.org/W2152415671","doi":"https://doi.org/10.1109/asru.2009.5373454","title":"Improved decision trees for multi-stream HMM-based audio-visual continuous speech recognition","display_name":"Improved decision trees for multi-stream HMM-based audio-visual continuous speech recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2152415671","doi":"https://doi.org/10.1109/asru.2009.5373454","mag":"2152415671"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5018240777","display_name":"Jing Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jing Huang","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045869355","display_name":"Karthik Visweswariah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Karthik Visweswariah","raw_affiliation_strings":["IBM India Research Laboratory, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM India Research Laboratory, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018240777"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":0.3525,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60363956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"228","last_page":"231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8056018948554993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7902315258979797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7613077163696289},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.6834002733230591},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6048653721809387},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5222223997116089},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.48808133602142334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48675990104675293},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.458322674036026},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.440576434135437},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.30967390537261963},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.2984760105609894},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.284201443195343},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.098441481590271}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8056018948554993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902315258979797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7613077163696289},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6834002733230591},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6048653721809387},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5222223997116089},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.48808133602142334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48675990104675293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.458322674036026},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.440576434135437},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.30967390537261963},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2984760105609894},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.284201443195343},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.098441481590271},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5373454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W39452988","https://openalex.org/W124185092","https://openalex.org/W171560785","https://openalex.org/W1498476715","https://openalex.org/W1560013842","https://openalex.org/W1584924955","https://openalex.org/W1586674080","https://openalex.org/W1599408644","https://openalex.org/W1948894153","https://openalex.org/W2002591263","https://openalex.org/W2074796660","https://openalex.org/W2096391593","https://openalex.org/W2096466030","https://openalex.org/W2116047093","https://openalex.org/W2121486117","https://openalex.org/W2121551559","https://openalex.org/W2132999255","https://openalex.org/W2133115605","https://openalex.org/W2135762233","https://openalex.org/W2169528353","https://openalex.org/W2395273492","https://openalex.org/W2487271655","https://openalex.org/W3099202502","https://openalex.org/W4299901747","https://openalex.org/W6605059668","https://openalex.org/W6629987738","https://openalex.org/W6633431331","https://openalex.org/W6635121317","https://openalex.org/W6678395162","https://openalex.org/W6712039779"],"related_works":["https://openalex.org/W4253235840","https://openalex.org/W2488941600","https://openalex.org/W1531133616","https://openalex.org/W2164637175","https://openalex.org/W2131711534","https://openalex.org/W2341426843","https://openalex.org/W3210917154","https://openalex.org/W1583620810","https://openalex.org/W2343205865","https://openalex.org/W642007152"],"abstract_inverted_index":{"HMM-based":[0,39],"audio-visual":[1],"speech":[2,11],"recognition":[3,12],"(AVSR)":[4],"systems":[5],"have":[6,45],"shown":[7],"success":[8],"in":[9,20,38,89,113,142],"continuous":[10,111],"by":[13,127],"combining":[14],"visual":[15,43,78,96,136,148],"and":[16,77,135],"audio":[17,55,76,134],"information,":[18],"especially":[19],"noisy":[21],"environments.":[22],"In":[23,58],"this":[24,59],"paper":[25,60],"we":[26,61,82,115],"study":[27],"how":[28],"to":[29,34,69],"improve":[30],"decision":[31,67,91,130,143],"trees":[32,68,131],"used":[33],"create":[35],"context":[36,51,72],"classes":[37,52,73,88,141],"AVSR":[40,125],"systems.":[41],"Traditionally,":[42],"models":[44],"been":[46],"trained":[47],"with":[48,100],"the":[49,54,63,71,75,84,90,95,133,147],"same":[50],"as":[53],"only":[56],"models.":[57],"investigate":[62,83],"use":[64,85],"of":[65,86,110],"separate":[66,129],"model":[70],"for":[74,94,132,146],"streams":[79,137],"independently.":[80],"Additionally":[81],"viseme":[87,140],"tree":[92,144],"building":[93,145],"stream.":[97,149],"On":[98],"experiments":[99],"a":[101,118],"37-speaker":[102],"1.5":[103],"hours":[104],"test":[105],"set":[106],"(about":[107],"12000":[108],"words)":[109],"digits":[112],"noise,":[114],"obtain":[116],"about":[117],"3%":[119],"absolute":[120],"(20%":[121],"relative)":[122],"gain":[123],"on":[124],"performance":[126],"using":[128,139],"when":[138]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}