{"id":"https://openalex.org/W2105605324","doi":"https://doi.org/10.1109/icassp.2012.6288961","title":"Combining eigenvoice speaker modeling and VTS-based environment compensation for robust speech recognition","display_name":"Combining eigenvoice speaker modeling and VTS-based environment compensation for robust speech recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2105605324","doi":"https://doi.org/10.1109/icassp.2012.6288961","mag":"2105605324"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5010173604","display_name":"Zhijian Ou","orcid":"https://orcid.org/0000-0002-9018-5074"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhijian Ou","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090357400","display_name":"Kan Deng","orcid":"https://orcid.org/0000-0002-3550-2268"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kan Deng","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, CHINA#TAB#","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010173604"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.4281,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72928839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4673","last_page":"4676"},"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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":0.805888295173645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7268283367156982},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.512586772441864},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46116015315055847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4335881769657135},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3882288336753845}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.805888295173645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268283367156982},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.512586772441864},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46116015315055847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4335881769657135},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3882288336753845},{"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/icassp.2012.6288961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1665196592","https://openalex.org/W1978647565","https://openalex.org/W2146871184","https://openalex.org/W2147143213","https://openalex.org/W2148331133","https://openalex.org/W2151484683","https://openalex.org/W2155445312","https://openalex.org/W2163253509","https://openalex.org/W2165108269","https://openalex.org/W2294327763"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W2033914206","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W2042327336","https://openalex.org/W289407349","https://openalex.org/W2368768466"],"abstract_inverted_index":{"Eigenvoice":[0],"and":[1,12,18,34,71,96,98,104],"vector":[2],"Taylor":[3],"series":[4],"(VTS)":[5],"are":[6,76],"good":[7],"models":[8],"for":[9,42,102],"speaker":[10,17,40,66,103],"differences":[11],"environmental":[13,19],"variations":[14],"separately.":[15],"However,":[16],"variation":[20],"always":[21],"coexist":[22],"in":[23,79],"real-world":[24],"speech.":[25],"In":[26,51],"this":[27],"paper,":[28],"we":[29,37],"propose":[30],"to":[31,59],"combine":[32],"eigenvoice":[33,39,69,95],"VTS.":[35],"Specifically,":[36],"introduce":[38],"modeling":[41,58],"the":[43,53,61,72,80,86,90],"clean":[44,62],"speech":[45],"into":[46],"VTS's":[47],"nonlinear":[48],"mismatch":[49],"function.":[50],"contrast,":[52],"standard":[54],"VTS":[55,97],"uses":[56],"speaker-independent":[57],"represent":[60],"speech,":[63],"regardless":[64],"of":[65,93],"differences.":[67],"The":[68],"coefficients":[70],"noise":[73,105],"model":[74],"parameters":[75],"jointly":[77],"estimated":[78],"new":[81],"approach.":[82],"Experimental":[83],"results":[84],"on":[85],"Aurora2":[87],"task":[88],"show":[89],"improved":[91],"performances":[92],"combining":[94],"demonstrate":[99],"its":[100],"ability":[101],"factorization.":[106]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}