{"id":"https://openalex.org/W2137069055","doi":"https://doi.org/10.1109/asru.2007.4430083","title":"Robust speech recognition using noise suppression based on multiple composite models and multi-pass search","display_name":"Robust speech recognition using noise suppression based on multiple composite models and multi-pass search","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2137069055","doi":"https://doi.org/10.1109/asru.2007.4430083","mag":"2137069055"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & 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/A5061510158","display_name":"Takatoshi Jitsuhiro","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Takatoshi Jitsuhiro","raw_affiliation_strings":["ATR Knowledge Science Laboratories, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Knowledge Science Laboratories, Kyoto, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108384524","display_name":"Tomoji Toriyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoji Toriyama","raw_affiliation_strings":["ATR Knowledge Science Laboratories, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Knowledge Science Laboratories, Kyoto, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012520388","display_name":"Kiyoshi Kogure","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiyoshi Kogure","raw_affiliation_strings":["ATR Knowledge Science Laboratories, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Knowledge Science Laboratories, Kyoto, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061510158"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4323,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.90493206,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"58"},"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":0.9997000098228455,"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":0.9990000128746033,"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/speech-recognition","display_name":"Speech recognition","score":0.774418830871582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7474381327629089},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.7317861914634705},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5975241661071777},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4964373707771301},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.46532532572746277},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42646458745002747},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41013622283935547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40004831552505493},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.388838529586792},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18645572662353516},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09375947713851929}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.774418830871582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474381327629089},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7317861914634705},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5975241661071777},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4964373707771301},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.46532532572746277},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42646458745002747},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41013622283935547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40004831552505493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.388838529586792},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18645572662353516},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09375947713851929},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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.2007.4430083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W35070573","https://openalex.org/W105750483","https://openalex.org/W198149826","https://openalex.org/W1502737068","https://openalex.org/W1665196592","https://openalex.org/W1970501224","https://openalex.org/W1988572375","https://openalex.org/W2098634964","https://openalex.org/W2100969003","https://openalex.org/W2128653836","https://openalex.org/W2149669758","https://openalex.org/W2466740398","https://openalex.org/W6601391444","https://openalex.org/W6630013100"],"related_works":["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","https://openalex.org/W4297807400"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"robust":[3],"speech":[4,29,31,43,72,81],"recognition":[5,32,44],"using":[6,116,133],"a":[7],"noise":[8,24,65,77,83,97,109],"suppression":[9,110],"method":[10,140],"based":[11,111],"on":[12,112],"multi-model":[13],"compositions":[14],"and":[15,27,82,99,105,137],"multi-pass":[16,88],"search.":[17],"In":[18],"real":[19],"environments,":[20],"many":[21,62,94],"kinds":[22,63,95],"of":[23,45,64,96],"signals":[25,66],"exists,":[26],"input":[28],"for":[30],"systems":[33],"include":[34],"them.":[35],"Our":[36],"task":[37],"in":[38],"the":[39,117,134,138,142],"E-Nightingale":[40,135],"project":[41],"is":[42,73,114],"voice":[46],"memoranda":[47],"spoken":[48],"by":[49,122],"nurses":[50],"during":[51],"actual":[52],"work":[53],"at":[54,67],"hospitals.":[55],"To":[56],"obtain":[57],"good":[58],"recognized":[59,123],"candidates,":[60],"suppressing":[61],"once":[68],"to":[69,79],"find":[70,80],"target":[71],"important.":[74],"First,":[75],"before":[76],"suppression,":[78],"label":[84,124],"sequences,":[85],"we":[86],"introduce":[87],"search":[89],"with":[90,126],"acoustic":[91],"models":[92,98,113,120],"including":[93],"their":[100,102,106],"compositions,":[101],"n-gram":[103],"models,":[104],"lexicon.":[107],"Second,":[108],"performed":[115],"multiple":[118],"composite":[119],"selected":[121],"sequences":[125],"time":[127],"alignments.":[128],"We":[129],"evaluated":[130],"this":[131],"approach":[132],"task,":[136],"proposed":[139],"outperformed":[141],"conventional":[143],"method.":[144]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}