{"id":"https://openalex.org/W2288669569","doi":"https://doi.org/10.1109/asru.2015.7404825","title":"Unified ASR system using LGM-based source separation, noise-robust feature extraction, and word hypothesis selection","display_name":"Unified ASR system using LGM-based source separation, noise-robust feature extraction, and word hypothesis selection","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2288669569","doi":"https://doi.org/10.1109/asru.2015.7404825","mag":"2288669569"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","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/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd"],"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057295313","display_name":"Ryoichi Takashima","orcid":"https://orcid.org/0000-0002-9808-0250"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoichi Takashima","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd"],"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068174033","display_name":"Takeshi Homma","orcid":"https://orcid.org/0000-0003-3864-3848"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Homma","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd"],"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084590882","display_name":"Rintaro Ikeshita","orcid":"https://orcid.org/0000-0003-2608-1999"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rintaro Ikeshita","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd"],"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052394367","display_name":"Yohei Kawaguchi","orcid":"https://orcid.org/0000-0002-2329-5441"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yohei Kawaguchi","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd"],"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084618194","display_name":"Takashi Sumiyoshi","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Sumiyoshi","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd"],"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009546381","display_name":"Takashi Endo","orcid":"https://orcid.org/0000-0002-4580-1704"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Endo","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd"],"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021883714","display_name":"Masahito Togami","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahito Togami","raw_affiliation_strings":["Research and Development Group, Hitachi, Ltd"],"affiliations":[{"raw_affiliation_string":"Research and Development Group, Hitachi, Ltd","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5044818016"],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":null,"apc_paid":null,"fwci":2.5847,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90729944,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"39","issue":null,"first_page":"416","last_page":"422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9994000196456909,"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":0.9983000159263611,"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":0.7702827453613281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5936561822891235},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5734106302261353},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5511507391929626},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5162015557289124},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5072769522666931},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4859405755996704},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4697972238063812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4648780822753906},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.46475329995155334},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.41654402017593384},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41351601481437683},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11640089750289917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7702827453613281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5936561822891235},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5734106302261353},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5511507391929626},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5162015557289124},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5072769522666931},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4859405755996704},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4697972238063812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4648780822753906},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.46475329995155334},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.41654402017593384},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41351601481437683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11640089750289917},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2015.7404825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1500860679","https://openalex.org/W1506558619","https://openalex.org/W1548802052","https://openalex.org/W1904457459","https://openalex.org/W2015767736","https://openalex.org/W2031583051","https://openalex.org/W2035927681","https://openalex.org/W2049633694","https://openalex.org/W2062164080","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2127000566","https://openalex.org/W2128653836","https://openalex.org/W2132187443","https://openalex.org/W2143027228","https://openalex.org/W2147768505","https://openalex.org/W2289394825","https://openalex.org/W2328757576","https://openalex.org/W3129711340","https://openalex.org/W3147539069","https://openalex.org/W4205778870","https://openalex.org/W6679619477","https://openalex.org/W6702079475"],"related_works":["https://openalex.org/W1569283511","https://openalex.org/W2380784125","https://openalex.org/W4236193183","https://openalex.org/W3004057759","https://openalex.org/W2889085215","https://openalex.org/W2914806737","https://openalex.org/W2053866214","https://openalex.org/W2607505004","https://openalex.org/W2231795205","https://openalex.org/W2944691285"],"abstract_inverted_index":{"In":[0,108],"this":[1,109],"paper,":[2,110],"we":[3,111],"propose":[4],"a":[5,53,60,156],"unified":[6],"system":[7,183,198],"that":[8,51,68,113,166,195],"incorporates":[9],"speech":[10,15,72],"source":[11,43,130],"separation":[12,44,131],"and":[13,59,100,159],"automatic":[14],"recognition":[16,145],"for":[17,142],"various":[18],"noise":[19],"environments.":[20],"There":[21],"are":[22],"three":[23],"features":[24,99,102],"in":[25,103,200],"the":[26,33,37,46,70,74,80,90,104,114,129,137,167,172,187,196,206],"proposed":[27,34,91,115,148,168,182,197],"system.":[28,208],"The":[29,86,133,147,162,181],"first":[30],"feature":[31,88,135],"of":[32,89,203],"method":[35,50,58,78,92,117,141,150,170],"is":[36,93,118,136,184],"LGM":[38],"(local":[39],"Gaussian":[40],"modeling)":[41],"based":[42,57,63,154],"with":[45,73,96],"efficient":[47],"permutation":[48],"alignment":[49],"integrates":[52],"power":[54],"spectrum":[55],"correlation":[56],"direction-of-arrival":[61],"(DOA)":[62],"method.":[64,180],"Evaluation":[65,192],"results":[66,164,193],"show":[67,112,165,194],"using":[69,186],"separated":[71],"baseline":[75,207],"acoustic":[76,105],"modeling":[77,106],"reduces":[79],"word":[81,138],"error":[82,177],"rate":[83],"(WER)":[84],"significantly.":[85],"second":[87],"multi-condition":[94],"training":[95,116],"per-utterance":[97],"normalized":[98],"noise-aware":[101],"step.":[107,132],"effective":[119],"even":[120],"when":[121],"an":[122,201],"input":[123],"signal":[124],"has":[125],"been":[126],"distorted":[127],"through":[128],"third":[134,188],"hypothesis":[139],"selection":[140,149,169],"integrating":[143],"multiple":[144],"results.":[146],"estimates":[151],"correct":[152],"words":[153],"on":[155],"recognizer's":[157],"confidence":[158],"co-occurrence":[160],"characteristics.":[161],"evaluation":[163],"outperforms":[171],"conventional":[173],"recognizer":[174],"output":[175],"voting":[176],"reduction":[178],"(ROVER)":[179],"evaluated":[185],"CHiME":[189],"challenge":[190],"dataset.":[191],"resulted":[199],"improvement":[202],"66.1%":[204],"over":[205]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}