{"id":"https://openalex.org/W2155235642","doi":"https://doi.org/10.21437/interspeech.2004-307","title":"Automatic speech recognition of co-channel speech: integrated speaker and speech recognition approach","display_name":"Automatic speech recognition of co-channel speech: integrated speaker and speech recognition approach","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W2155235642","doi":"https://doi.org/10.21437/interspeech.2004-307","mag":"2155235642"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-307","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5003679010","display_name":"Larry Heck","orcid":"https://orcid.org/0000-0003-3358-6362"},"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":"Larry Heck","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/A5113924071","display_name":"M. Mao","orcid":"https://orcid.org/0009-0005-4041-0068"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Mao","raw_affiliation_strings":["Stanford University ()"],"affiliations":[{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003679010"],"corresponding_institution_ids":["https://openalex.org/I4210125787"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.13765024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"829","last_page":"832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9945999979972839,"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/T12031","display_name":"Speech and dialogue systems","score":0.9869999885559082,"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/speech-recognition","display_name":"Speech recognition","score":0.7924182415008545},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7643659114837646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.755890965461731},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5579847693443298},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5370819568634033},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46259158849716187},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.44755908846855164},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4420895576477051},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.24324196577072144}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7924182415008545},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7643659114837646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755890965461731},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5579847693443298},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5370819568634033},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46259158849716187},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.44755908846855164},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4420895576477051},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.24324196577072144}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-307","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.655.6905","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.655.6905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mirlab.org/conference_papers/International_Conference/ICSLP+2004/contents/WeA_pdf/WeA1705o/WeA1705o.6_p1235.pdf?origin%3Dpublication_detail","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4000000059604645,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W205402702","https://openalex.org/W1563235770","https://openalex.org/W1838773786","https://openalex.org/W1869017930","https://openalex.org/W2098773974","https://openalex.org/W2123409957","https://openalex.org/W2141673075","https://openalex.org/W2160381028","https://openalex.org/W2170491071","https://openalex.org/W2394963835"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W134179020","https://openalex.org/W359143747"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,23,55,59,68,74,82,87,95,121,129],"novel":[4],"Bayesian":[5],"approach":[6],"to":[7],"the":[8,18,22,27,31,35,43,50,63,71,79,90,98,102],"problem":[9,14],"of":[10,21,26,52,67,73,76,81,94,101,117,128],"co-channel":[11,118],"speech.":[12],"The":[13],"is":[15,40,110],"for-mulated":[16],"as":[17,49],"joint":[19,44],"maximization":[20],"posteriori":[24],"probability":[25,45],"word":[28,125],"sequence":[29,75],"and":[30,97],"target":[32],"speaker":[33,69],"given":[34],"observed":[36],"speech":[37,61,119],"signal.":[38],"It":[39],"shown":[41],"that":[42],"can":[46],"be":[47],"expressed":[48],"product":[51],"six":[53],"terms:":[54],"likelihood":[56,65,72,80],"score":[57,66],"from":[58],"speaker-independent":[60],"recognizer,":[62,70],"(normalized)":[64],"prosodic":[77],"events,":[78],"speaker-dependent":[83],"statistical":[84],"language":[85],"model,":[86],"prior":[88,99],"representing":[89],"chan-nel":[91],"usage":[92],"patterns":[93],"speaker,":[96],"probabil-ity":[100],"speaker.":[103],"An":[104],"efficient":[105],"single-pass":[106],"Viterbi":[107],"search":[108],"strategy":[109],"presented.":[111],"Experimental":[112],"results":[113],"on":[114],"over-the-telephone":[115],"recognition":[116],"show":[120],"45%":[122],"reduction":[123],"in":[124],"error":[126],"rate":[127],"10-digit":[130],"telephone":[131],"num-ber":[132],"task.":[133],"1.":[134]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}