{"id":"https://openalex.org/W159519692","doi":"https://doi.org/10.21437/interspeech.2009-361","title":"Target speech GMM-based spectral compensation for noise robust speech recognition","display_name":"Target speech GMM-based spectral compensation for noise robust speech recognition","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W159519692","doi":"https://doi.org/10.21437/interspeech.2009-361","mag":"159519692"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-361","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100590171","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009532108","display_name":"Sadaoki Furui","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sadaoki Furui","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1255","last_page":"1258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7911920547485352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7247123718261719},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5846042633056641},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5307775735855103},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5109390616416931},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5092259645462036},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48939695954322815},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46100327372550964},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4369519054889679},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4272436201572418},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42281949520111084},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4172791540622711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4105580449104309},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08083435893058777}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7911920547485352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247123718261719},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5846042633056641},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5307775735855103},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5109390616416931},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5092259645462036},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48939695954322815},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46100327372550964},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4369519054889679},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4272436201572418},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42281949520111084},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4172791540622711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4105580449104309},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08083435893058777},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-361","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50081618","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100590171","pdf_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100590171","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:t2r2.star.titech.ac.jp:50081618","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100590171","pdf_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100590171","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W159519692.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W92058","https://openalex.org/W35070573","https://openalex.org/W1932968309","https://openalex.org/W2002342963","https://openalex.org/W2050693797","https://openalex.org/W2056623441","https://openalex.org/W2069976350","https://openalex.org/W2082474452","https://openalex.org/W2109111030","https://openalex.org/W2121981798","https://openalex.org/W2128653836","https://openalex.org/W2142416747","https://openalex.org/W2151046618","https://openalex.org/W2161078696","https://openalex.org/W2397315227"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W4229940372","https://openalex.org/W1523214805","https://openalex.org/W4294771049","https://openalex.org/W2559040841","https://openalex.org/W2341426843","https://openalex.org/W2131711534","https://openalex.org/W4389247473","https://openalex.org/W2154415461"],"abstract_inverted_index":{"Abstract":[0],"To":[1],"improve":[2],"speech":[3,30,51,132],"recognition":[4,117],"performance":[5,118],"in":[6,18,47,56],"adverse":[7],"condi-tions,":[8],"a":[9,66,87,95],"noise":[10],"compensation":[11],"method":[12,64,124],"is":[13,38,71,102,119],"proposed":[14,63],"that":[15,39,70,114],"applies":[16],"atransformation":[17],"the":[19,48,107,122],"spectral":[20,92,126],"domain":[21,58],"whose":[22],"parameters":[23],"are":[24,53],"op-timized":[25],"based":[26],"on":[27,33],"likelihood":[28],"of":[29],"GMM":[31],"modeled":[32,55],"thefeature":[34,57],"domain.":[35],"The":[36,62],"idea":[37],"additive":[40],"and":[41,76,83],"convolutionalnoises":[42],"have":[43],"mathematically":[44],"simple":[45],"expression":[46],"spectraldomain":[49],"while":[50],"characteristics":[52],"better":[54],"such":[59],"as":[60,94],"MFCC.":[61],"worksas":[65],"feature":[67],"extraction":[68],"front-end":[69],"independent":[72],"from":[73],"de-coding":[74],"engine,":[75],"has":[77,111],"ability":[78],"to":[79],"compensate":[80],"for":[81],"non-stationaryadditive":[82],"convolutional":[84],"noises":[85],"with":[86],"short":[88],"time":[89],"delay.":[90],"Itincludes":[91],"subtraction":[93],"special":[96],"case":[97],"when":[98],"no":[99],"param-eter":[100],"optimization":[101],"performed.":[103],"Experiments":[104],"were":[105],"performedusing":[106],"AURORA-2J":[108],"database.":[109],"It":[110],"been":[112],"shown":[113],"signif-icantly":[115],"higher":[116],"obtained":[120],"by":[121],"pro-posed":[123],"than":[125],"subtraction.":[127],"Index":[128],"Terms":[129],":":[130],"noisy":[131],"recognition,":[133],"spectrum,":[134],"Gaussianmixture":[135],"model":[136]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}