{"id":"https://openalex.org/W2962751625","doi":"https://doi.org/10.1109/apsipa.2015.7415306","title":"Improved deep speaker feature learning for text-dependent speaker recognition","display_name":"Improved deep speaker feature learning for text-dependent speaker recognition","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2962751625","doi":"https://doi.org/10.1109/apsipa.2015.7415306","mag":"2962751625"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2015.7415306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"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":"Lantian Li","raw_affiliation_strings":["Division of Technical Innovation and Development, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Division of Technical Innovation and Development, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007215401","display_name":"Yiye Lin","orcid":null},"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":"Yiye Lin","raw_affiliation_strings":["Division of Technical Innovation and Development, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Division of Technical Innovation and Development, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352621","display_name":"Zhiyong Zhang","orcid":"https://orcid.org/0000-0003-3061-7768"},"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":"Zhiyong Zhang","raw_affiliation_strings":["Division of Technical Innovation and Development, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Division of Technical Innovation and Development, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"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":"Dong Wang","raw_affiliation_strings":["Division of Technical Innovation and Development, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Division of Technical Innovation and Development, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050701255"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.7458,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95404319,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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/T10860","display_name":"Speech and Audio Processing","score":0.9958999752998352,"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/speaker-recognition","display_name":"Speaker recognition","score":0.7922008037567139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7902005314826965},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7429873943328857},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6790762543678284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6306806802749634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5297252535820007},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4690834581851959},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4139249920845032},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38251394033432007},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3816797137260437},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12820574641227722}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7922008037567139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902005314826965},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7429873943328857},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6790762543678284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6306806802749634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5297252535820007},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4690834581851959},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4139249920845032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38251394033432007},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3816797137260437},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12820574641227722},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2015.7415306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W116902681","https://openalex.org/W1589137271","https://openalex.org/W2013598660","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2077548500","https://openalex.org/W2107638917","https://openalex.org/W2112582577","https://openalex.org/W2147147599","https://openalex.org/W2154278880","https://openalex.org/W2183016404","https://openalex.org/W6604828220"],"related_works":["https://openalex.org/W3159007498","https://openalex.org/W4245011087","https://openalex.org/W2105667909","https://openalex.org/W1996443744","https://openalex.org/W2540618545","https://openalex.org/W2016461833","https://openalex.org/W2795346515","https://openalex.org/W2329090855","https://openalex.org/W2102293963","https://openalex.org/W2018489529"],"abstract_inverted_index":{"A":[0],"deep":[1,15,62],"learning":[2,63],"approach":[3,20,77],"has":[4,21],"been":[5,22],"proposed":[6,94],"recently":[7],"to":[8,24,69],"derive":[9],"speaker":[10,26,88],"identifies":[11],"(d-vector)":[12],"by":[13],"a":[14,65,74,86],"neural":[16],"network":[17],"(DNN).":[18],"This":[19,55],"applied":[23],"text-dependent":[25,87],"recognition":[27,89],"tasks":[28],"and":[29,73],"shows":[30],"reasonable":[31],"performance":[32,99],"gains":[33],"when":[34],"combined":[35],"with":[36,51],"the":[37,43,52,61,93,102],"conventional":[38],"i-vector":[39,53],"approach.":[40],"Although":[41],"promising,":[42],"existing":[44,103],"d-vector":[45,104],"implementation":[46],"still":[47],"can":[48,96],"not":[49],"compete":[50],"baseline.":[54],"paper":[56],"presents":[57],"two":[58],"improvements":[59],"for":[60],"approach:":[64],"phone-dependent":[66],"DNN":[67],"structure":[68],"normalize":[70],"phone":[71],"variation,":[72],"new":[75],"scoring":[76],"based":[78],"on":[79,85],"dynamic":[80],"time":[81],"warping":[82],"(DTW).":[83],"Experiments":[84],"task":[90],"demonstrated":[91],"that":[92],"methods":[95],"provide":[97],"considerable":[98],"improvement":[100],"over":[101],"implementation.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}