{"id":"https://openalex.org/W3016234652","doi":"https://doi.org/10.1109/icassp40776.2020.9053258","title":"Toward Better Speaker Embeddings: Automated Collection of Speech Samples From Unknown Distinct Speakers","display_name":"Toward Better Speaker Embeddings: Automated Collection of Speech Samples From Unknown Distinct Speakers","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016234652","doi":"https://doi.org/10.1109/icassp40776.2020.9053258","mag":"3016234652"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5046030806","display_name":"Tam Minh Pham","orcid":"https://orcid.org/0000-0002-5899-9537"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minh Pham","raw_affiliation_strings":["Department of Computer Science, Worcester Polytechnic Institute (WPI)"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Worcester Polytechnic Institute (WPI)","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044787071","display_name":"Zeqian Li","orcid":"https://orcid.org/0000-0002-0884-8028"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeqian Li","raw_affiliation_strings":["Department of Computer Science, Worcester Polytechnic Institute (WPI)"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Worcester Polytechnic Institute (WPI)","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027788582","display_name":"Jacob Whitehill","orcid":"https://orcid.org/0000-0002-5851-312X"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Whitehill","raw_affiliation_strings":["Department of Computer Science, Worcester Polytechnic Institute (WPI)"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Worcester Polytechnic Institute (WPI)","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046030806"],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75075507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7089","last_page":"7093"},"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/T11309","display_name":"Music 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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7905944585800171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7894270420074463},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7560060620307922},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7100142240524292},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5422325134277344},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5212072134017944},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4856902062892914},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47862592339515686},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4279513359069824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3530007600784302}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7905944585800171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894270420074463},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7560060620307922},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7100142240524292},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5422325134277344},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5212072134017944},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4856902062892914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47862592339515686},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4279513359069824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3530007600784302},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1987302197","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2096733369","https://openalex.org/W2112575355","https://openalex.org/W2115252128","https://openalex.org/W2150769028","https://openalex.org/W2191779130","https://openalex.org/W2341528187","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2962788625","https://openalex.org/W3099206234","https://openalex.org/W3101998545","https://openalex.org/W6631362777","https://openalex.org/W6677618333"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"The":[0],"accuracy":[1],"of":[2,12,27,40,95],"speaker":[3,14],"verification":[4],"and":[5,59],"diarization":[6],"models":[7],"depends":[8],"on":[9,72,99,106],"the":[10,13,25,61,93],"quality":[11,94],"embeddings":[15,96],"used":[16],"to":[17,102],"separate":[18],"audio":[19],"samples":[20,42],"from":[21,43],"different":[22],"speakers.":[23],"With":[24,54],"goal":[26],"training":[28],"better":[29],"embedding":[30],"models,":[31],"we":[32,57,87],"devise":[33],"an":[34],"automatic":[35],"pipeline":[36],"for":[37],"large-scale":[38],"collection":[39],"speech":[41],"unique":[44,79],"speakers":[45],"that":[46,74],"is":[47],"significantly":[48],"more":[49],"automated":[50],"than":[51],"previous":[52],"approaches.":[53],"this":[55,82],"pipeline,":[56],"collect":[58],"publish":[60],"BookTubeSpeech":[62],"dataset,":[63],"containing":[64],"8,450":[65],"YouTube":[66],"videos":[67],"(7.74":[68],"min":[69],"per":[70],"video":[71],"average)":[73],"each":[75],"contains":[76],"a":[77,89,103],"single":[78],"speaker.":[80],"Using":[81],"dataset":[83],"combined":[84],"with":[85],"VoxCeleb2,":[86],"show":[88],"substantial":[90],"improvement":[91],"in":[92],"when":[97],"tested":[98],"LibriSpeech":[100],"compared":[101],"model":[104],"trained":[105],"only":[107],"VoxCeleb2.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}