{"id":"https://openalex.org/W2139899299","doi":"https://doi.org/10.1109/icassp.2008.4518751","title":"Feature enhancement by speaker-normalized splice for robust speech recognition","display_name":"Feature enhancement by speaker-normalized splice for robust speech recognition","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2139899299","doi":"https://doi.org/10.1109/icassp.2008.4518751","mag":"2139899299"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518751","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5109365728","display_name":"Yusuke Shinohara","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yusuke Shinohara","raw_affiliation_strings":["Toshiba Corporate Research and Development Center, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Toshiba Corporate Research and Development Center, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064866374","display_name":"Takashi Masuko","orcid":"https://orcid.org/0000-0002-2410-2007"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Masuko","raw_affiliation_strings":["Toshiba Corporate Research and Development Center, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Toshiba Corporate Research and Development Center, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112250968","display_name":"Masami Akamine","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masami Akamine","raw_affiliation_strings":["Toshiba Corporate Research and Development Center, Kawasaki, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Toshiba Corporate Research and Development Center, Kawasaki, Kanagawa, Japan","institution_ids":["https://openalex.org/I1292669757"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109365728"],"corresponding_institution_ids":["https://openalex.org/I1292669757"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.15942029,"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":"4881","last_page":"4884"},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/normalization","display_name":"Normalization (sociology)","score":0.8547749519348145},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7136932015419006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7119897603988647},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6282331943511963},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5970185995101929},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5647034049034119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5645195841789246},{"id":"https://openalex.org/keywords/splice","display_name":"splice","score":0.5622414946556091},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5169643759727478},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5165490508079529},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.516079843044281},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48796695470809937},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45815718173980713},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.44652464985847473}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8547749519348145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7136932015419006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7119897603988647},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6282331943511963},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5970185995101929},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5647034049034119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5645195841789246},{"id":"https://openalex.org/C2780989783","wikidata":"https://www.wikidata.org/wiki/Q7578557","display_name":"splice","level":3,"score":0.5622414946556091},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5169643759727478},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5165490508079529},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.516079843044281},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48796695470809937},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45815718173980713},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.44652464985847473},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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.2008.4518751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518751","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W84880661","https://openalex.org/W1488465960","https://openalex.org/W1599512239","https://openalex.org/W1665196592","https://openalex.org/W2002342963","https://openalex.org/W2080921589","https://openalex.org/W2121973264","https://openalex.org/W2121981798","https://openalex.org/W2151484683","https://openalex.org/W3147539069","https://openalex.org/W6603374476","https://openalex.org/W6682194319"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1521049138"],"abstract_inverted_index":{"The":[0,64,111],"SPLICE":[1,49,57],"method":[2,113],"of":[3,25,56,60,106,126],"feature":[4,20,30],"enhancement":[5],"is":[6,41,62,67,78,88,100],"known":[7],"for":[8,90],"its":[9,86],"powerful":[10],"performance.":[11],"It":[12],"learns":[13],"a":[14,23,76,83,97,103,120],"mapping":[15,77],"from":[16],"noisy":[17],"to":[18,45,72],"clean":[19],"vectors":[21],"given":[22],"set":[24],"stereo":[26],"training":[27,65],"data.":[28],"However,":[29],"vector":[31],"variation":[32],"caused":[33],"by":[34,58],"speaker":[35,73,99,108],"changes":[36],"conceals":[37],"noise-induced":[38],"variation,":[39,74],"which":[40],"what":[42],"we":[43],"want":[44],"find":[46],"in":[47],"the":[48,91,94,107,129],"training.":[50,110],"In":[51],"this":[52],"paper,":[53],"an":[54],"improvement":[55],"means":[59],"speaker-normalization":[61],"proposed.":[63],"data":[66],"first":[68],"normalized":[69],"with":[70,82],"respect":[71],"and":[75,118],"learned":[79,101],"afterward.":[80],"CMLLR":[81],"GMM":[84,95],"as":[85],"target":[87],"utilized":[89],"speaker-normalization,":[92],"where":[93],"representing":[96],"standard":[98],"via":[102],"novel":[104],"variant":[105],"adaptive":[109],"proposed":[112],"was":[114],"evaluated":[115],"on":[116],"Aurora2,":[117],"achieved":[119],"relative":[121],"word":[122],"error":[123],"rate":[124],"reduction":[125],"38%":[127],"over":[128],"conventional":[130],"SPLICE.":[131]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
