{"id":"https://openalex.org/W1486956970","doi":"https://doi.org/10.1109/icassp.2005.1415204","title":"Cluster-Dependent Acoustic Modeling","display_name":"Cluster-Dependent Acoustic Modeling","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W1486956970","doi":"https://doi.org/10.1109/icassp.2005.1415204","mag":"1486956970"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5107249743","display_name":"Bing Xiang","orcid":"https://orcid.org/0009-0006-4028-4935"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bing Xiang","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048517713","display_name":"Long Nguyen","orcid":"https://orcid.org/0000-0002-0884-1635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Nguyen","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034173999","display_name":"Spyros Matsoukas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Matsoukas","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089653752","display_name":"Richard Schwartz","orcid":"https://orcid.org/0000-0002-4654-624X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R. Schwartz","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5107249743"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9036,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78778396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"677","last_page":"680"},"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/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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/T10860","display_name":"Speech and Audio Processing","score":0.9944999814033508,"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/decoding-methods","display_name":"Decoding methods","score":0.8434094190597534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7292423248291016},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7268402576446533},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6899045705795288},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6858354210853577},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6187037229537964},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5831782817840576},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5181723833084106},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5094659924507141},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.45171430706977844},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4488445222377777},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.42465221881866455},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.42402440309524536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3804372549057007},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24557197093963623},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09781667590141296},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08884862065315247}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8434094190597534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7292423248291016},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7268402576446533},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6899045705795288},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6858354210853577},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6187037229537964},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5831782817840576},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5181723833084106},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5094659924507141},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45171430706977844},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4488445222377777},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.42465221881866455},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.42402440309524536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3804372549057007},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24557197093963623},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09781667590141296},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08884862065315247},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1599512239","https://openalex.org/W1998462514","https://openalex.org/W2041823554","https://openalex.org/W2080400971","https://openalex.org/W2090861223","https://openalex.org/W2100969003","https://openalex.org/W2116903408","https://openalex.org/W2140914930","https://openalex.org/W2146049072","https://openalex.org/W2146871184","https://openalex.org/W2164031777","https://openalex.org/W6680972403"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1521049138"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,19,60],"present":[4],"cluster-dependent":[5,22],"acoustic":[6,16],"modeling":[7],"for":[8],"large-vocabulary":[9],"speech":[10],"recognition.":[11],"With":[12],"large":[13],"amounts":[14],"of":[15,30,64,93],"training":[17],"data,":[18],"build":[20],"multiple":[21],"models":[23],"(CDM),":[24],"each":[25,65],"focusing":[26],"on":[27,121],"a":[28,45],"group":[29],"speakers":[31],"in":[32,90,106,112],"order":[33],"to":[34,74,117],"represent":[35],"speaker-dependent":[36,48],"characteristics.":[37],"It":[38],"is":[39,51],"motivated":[40],"by":[41],"the":[42,54,62,91,122],"fact":[43],"that":[44],"sufficiently":[46],"trained":[47],"(SD)":[49],"model":[50,83],"better":[52],"than":[53,102],"speaker-independent":[55],"(SI)":[56],"model.":[57],"During":[58],"decoding,":[59],"decode":[61],"data":[63],"test":[66,127],"speaker":[67,80],"using":[68],"CDMs":[69],"selected":[70],"under":[71],"certain":[72],"criteria":[73],"achieve":[75],"high":[76],"recognition":[77],"accuracy.":[78],"Various":[79],"clustering":[81],"and":[82,88,109],"selection":[84],"techniques":[85],"are":[86],"proposed":[87],"compared":[89,116],"task":[92],"broadcast":[94],"news":[95],"(BN)":[96],"transcription.":[97],"The":[98],"CDM":[99],"provided":[100],"more":[101],"1%":[103],"absolute":[104],"gain":[105,111],"unadapted":[107],"decoding":[108,114],"0.5%":[110],"adapted":[113],"when":[115],"our":[118],"baseline":[119],"system":[120],"EARS":[123],"BN":[124],"2003":[125],"development":[126],"set.":[128]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}