{"id":"https://openalex.org/W2168132435","doi":"https://doi.org/10.1109/icassp.2005.1415206","title":"Automatic Training Set Segmentation for Multi-pass Speech Recognition","display_name":"Automatic Training Set Segmentation for Multi-pass Speech Recognition","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2168132435","doi":"https://doi.org/10.1109/icassp.2005.1415206","mag":"2168132435"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415206","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/A5113924071","display_name":"M. Mao","orcid":"https://orcid.org/0009-0005-4041-0068"},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M.Z. Mao","raw_affiliation_strings":["Nuance Communications, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Nuance Communications, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013813527","display_name":"Vincent Vanhoucke","orcid":"https://orcid.org/0000-0003-0544-2791"},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. Vanhoucke","raw_affiliation_strings":["Nuance Communications, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Nuance Communications, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001487094","display_name":"Brian Strope","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"B. Strope","raw_affiliation_strings":["Nuance Communications, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Nuance Communications, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210125787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113924071"],"corresponding_institution_ids":["https://openalex.org/I4210125787"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.14303388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"685","last_page":"688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9991999864578247,"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":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.7640414237976074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7398211359977722},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6840134263038635},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6291991472244263},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6266385912895203},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5734045505523682},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.554326057434082},{"id":"https://openalex.org/keywords/first-pass","display_name":"First pass","score":0.5431572198867798},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4970414936542511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4615846276283264},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4559735059738159},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44491592049598694},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3701218068599701},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09818944334983826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640414237976074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7398211359977722},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6840134263038635},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6291991472244263},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6266385912895203},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5734045505523682},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.554326057434082},{"id":"https://openalex.org/C2994044699","wikidata":"https://www.wikidata.org/wiki/Q1330121","display_name":"First pass","level":2,"score":0.5431572198867798},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4970414936542511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4615846276283264},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4559735059738159},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44491592049598694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3701218068599701},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09818944334983826},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415206","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":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W794766","https://openalex.org/W70088150","https://openalex.org/W1480376833","https://openalex.org/W1578604476","https://openalex.org/W1634005169","https://openalex.org/W1833248789","https://openalex.org/W2049633694","https://openalex.org/W2083393647","https://openalex.org/W2098773974","https://openalex.org/W2099111195","https://openalex.org/W2146871184","https://openalex.org/W2294327763","https://openalex.org/W6634752090","https://openalex.org/W6697408645","https://openalex.org/W7075705205"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2146197305","https://openalex.org/W2134950286","https://openalex.org/W4225329198"],"abstract_inverted_index":{"A":[0,47],"common":[1],"approach":[2],"to":[3,11,21,55],"automatic":[4,67],"speech":[5],"recognition":[6,9],"uses":[7],"two":[8,134],"passes":[10],"decode":[12],"an":[13,65],"utterance:":[14],"the":[15,19,28,32,59,79,85,98],"first":[16],"pass":[17,30,61,81,135],"limits":[18],"search":[20],"a":[22,109,132],"smaller":[23],"set":[24,34],"of":[25,108,140],"likely":[26],"hypotheses;":[27],"second":[29,60,80],"re-scores":[31],"limited":[33],"using":[35],"more":[36,110],"detailed":[37],"acoustic":[38,112],"models":[39],"which":[40,106],"may":[41],"target":[42],"gender":[43,73],"or":[44,74],"specific":[45],"channels.":[46],"question":[48],"raised":[49],"by":[50],"this":[51],"architecture":[52],"is":[53,103],"how":[54],"define":[56],"and":[57],"train":[58,78],"models.":[62],"We":[63],"describe":[64],"extensible":[66],"solution":[68],"that":[69],"requires":[70],"no":[71],"manual":[72],"channel":[75],"labeling.":[76],"To":[77],"models,":[82],"we":[83],"cluster":[84],"training":[86],"data":[87],"into":[88],"datasets":[89],"containing":[90],"utterances":[91],"whose":[92],"acoustics":[93],"are":[94,114],"very":[95],"similar":[96,138],"across":[97],"entire":[99],"utterance.":[100],"The":[101],"clustering":[102],"based":[104],"on":[105],"regions":[107],"general":[111],"model":[113,141],"activated":[115],"during":[116],"forced":[117],"alignments.":[118],"Experiments":[119],"with":[120,137],"commercial":[121],"American-English":[122],"digit":[123],"strings":[124],"show":[125],"9.3%":[126],"relative":[127],"error":[128],"rate":[129],"reduction":[130],"over":[131],"gender-based":[133],"system":[136],"numbers":[139],"parameters.":[142]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}