{"id":"https://openalex.org/W2401567014","doi":"https://doi.org/10.1109/icassp.2016.7472766","title":"Speech recognition robust against speech overlapping in monaural recordings of telephone conversations","display_name":"Speech recognition robust against speech overlapping in monaural recordings of telephone conversations","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2401567014","doi":"https://doi.org/10.1109/icassp.2016.7472766","mag":"2401567014"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5028421346","display_name":"Masayuki Suzuki","orcid":"https://orcid.org/0000-0002-0436-1490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masayuki Suzuki","raw_affiliation_strings":["Watson multimodal, IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson multimodal, IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["Watson multimodal, IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson multimodal, IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069028016","display_name":"Tohru Nagano","orcid":"https://orcid.org/0000-0002-3686-2791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tohru Nagano","raw_affiliation_strings":["Watson multimodal, IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson multimodal, IBM","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013412274","display_name":"Ryuki Tachibana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryuki Tachibana","raw_affiliation_strings":["Watson multimodal, IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson multimodal, IBM","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5685","last_page":"5689"},"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/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":0.9988999962806702,"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/monaural","display_name":"Monaural","score":0.9859576225280762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8410700559616089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8134797811508179},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4832404553890228},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.44602879881858826},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.41885966062545776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.347652405500412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33242154121398926},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09447982907295227},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.06838884949684143}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9859576225280762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8410700559616089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134797811508179},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4832404553890228},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.44602879881858826},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.41885966062545776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.347652405500412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33242154121398926},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09447982907295227},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.06838884949684143},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W258837700","https://openalex.org/W1555696814","https://openalex.org/W1557160870","https://openalex.org/W1558276682","https://openalex.org/W1821216667","https://openalex.org/W1821592834","https://openalex.org/W2001987918","https://openalex.org/W2033310064","https://openalex.org/W2053165762","https://openalex.org/W2062164080","https://openalex.org/W2068283348","https://openalex.org/W2081074144","https://openalex.org/W2115483887","https://openalex.org/W2119809277","https://openalex.org/W2132603781","https://openalex.org/W2136439176","https://openalex.org/W2155117693","https://openalex.org/W2158195707","https://openalex.org/W2167918566","https://openalex.org/W2169264834","https://openalex.org/W2169886347","https://openalex.org/W2489311264","https://openalex.org/W2541983972","https://openalex.org/W6633191483","https://openalex.org/W6658850935"],"related_works":["https://openalex.org/W2401567014","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"Monaural":[0],"(single-channel)":[1],"recording":[2,23,31],"is":[3,24,40,46,151,157],"sometimes":[4],"used":[5],"for":[6,140,167],"telephone":[7],"conversations":[8],"in":[9],"call":[10],"centers.":[11],"Generally":[12],"speaking,":[13],"the":[14,29,33,48,55,59,62,69,73,99,125,129,137,148,154],"accuracy":[15],"of":[16,20,28,32,61,87,104,142,164],"automatic":[17],"speech":[18,169],"recognition":[19,49],"a":[21,85],"monaural":[22,92,116,168],"worse":[25],"than":[26,115],"that":[27,47],"multi-channel":[30,105],"same":[34],"conversation":[35],"where":[36,58,124],"each":[37],"speaker's":[38],"voice":[39],"separately":[41],"recorded.":[42],"The":[43],"major":[44],"reason":[45],"system":[50],"fails":[51],"not":[52],"only":[53],"at":[54,68],"overlapping":[56,74],"segments":[57,71],"voices":[60],"multiple":[63],"speakers":[64],"overlap,":[65],"but":[66],"also":[67],"neighboring":[70],"surrounding":[72],"segments.":[75],"In":[76],"this":[77,81],"paper,":[78],"we":[79],"tackle":[80],"problem":[82],"by":[83,101,132],"using":[84],"combination":[86],"garbage":[88],"modeling":[89],"and":[90,107,118,144],"noise-robust":[91],"acoustic":[93],"modeling.":[94],"Our":[95],"proposed":[96,126,149,155],"method":[97,150,156],"trains":[98],"models":[100],"making":[102],"use":[103],"recordings":[106,117],"transcripts,":[108],"which":[109],"are":[110],"relatively":[111],"easy":[112,158],"to":[113,136,159,161],"prepare":[114],"transcripts.":[119],"We":[120],"present":[121],"experimental":[122],"results":[123],"methods":[127,139],"reduced":[128],"error":[130],"rates":[131],"approximately":[133],"3%":[134],"relative":[135],"baseline":[138],"both":[141],"GMM-HMM":[143],"CNN-HMM":[145],"cases.":[146],"Because":[147],"quite":[152],"simple,":[153],"deploy":[160],"wide":[162],"range":[163],"ASR":[165],"systems":[166],"transcription.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}