{"id":"https://openalex.org/W3046380034","doi":"https://doi.org/10.21437/interspeech.2020-1765","title":"A Comparative Re-Assessment of Feature Extractors for Deep Speaker Embeddings","display_name":"A Comparative Re-Assessment of Feature Extractors for Deep Speaker Embeddings","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3046380034","doi":"https://doi.org/10.21437/interspeech.2020-1765","mag":"3046380034"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1765","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1765","pdf_url":"https://www.isca-archive.org/interspeech_2020/liu20q_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2020/liu20q_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014303571","display_name":"Xuechen Liu","orcid":"https://orcid.org/0000-0003-1207-5651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuechen Liu","raw_affiliation_strings":["MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079693142","display_name":"Md Sahidullah","orcid":"https://orcid.org/0000-0002-0624-2903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md. Sahidullah","raw_affiliation_strings":["MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["University of Eastern Finland ( Educa, Tulliportinkatu 1, 80130 Joensuu, Finland - Finlande)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Eastern Finland ( Educa, Tulliportinkatu 1, 80130 Joensuu, Finland - Finlande)","institution_ids":["https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.84,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88527409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3221","last_page":"3225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9861000180244446,"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":0.9642000198364258,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8214730024337769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7525224685668945},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.7083189487457275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6923267841339111},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5810874104499817},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.551695704460144},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5453979969024658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.545086145401001},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5215944051742554},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.5125972628593445},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5068314671516418},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49466416239738464},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.48696169257164},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.46719786524772644},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3955151438713074},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.38930752873420715}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8214730024337769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525224685668945},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.7083189487457275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6923267841339111},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5810874104499817},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.551695704460144},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5453979969024658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.545086145401001},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5215944051742554},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.5125972628593445},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5068314671516418},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49466416239738464},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.48696169257164},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.46719786524772644},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3955151438713074},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.38930752873420715},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1765","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1765","pdf_url":"https://www.isca-archive.org/interspeech_2020/liu20q_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2020-1765","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1765","pdf_url":"https://www.isca-archive.org/interspeech_2020/liu20q_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3046380034.pdf","grobid_xml":"https://content.openalex.org/works/W3046380034.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W3119288895","https://openalex.org/W2359140082","https://openalex.org/W66821593","https://openalex.org/W2074132948"],"abstract_inverted_index":{"Modern":[0],"automatic":[1],"speaker":[2,84],"verification":[3],"relies":[4],"largely":[5],"on":[6,12,25,54],"deep":[7,83],"neural":[8],"networks":[9],"(DNNs)":[10],"trained":[11],"mel-frequency":[13],"cepstral":[14],"coefficient":[15],"(MFCC)":[16],"features.While":[17],"there":[18],"are":[19],"alternative":[20],"feature":[21,52],"extraction":[22],"methods":[23],"based":[24],"phase,":[26],"prosody":[27],"and":[28,56,73,93],"long-term":[29],"temporal":[30],"operations,":[31],"they":[32],"have":[33],"not":[34],"been":[35],"extensively":[36],"studied":[37],"with":[38,64],"DNN-based":[39],"methods.We":[40],"aim":[41],"to":[42,80,90,103],"fill":[43],"this":[44],"gap":[45],"by":[46],"providing":[47],"extensive":[48],"re-assessment":[49],"of":[50],"14":[51],"extractors":[53],"VoxCeleb":[55],"SITW":[57],"datasets.Our":[58],"findings":[59],"reveal":[60],"that":[61],"features":[62],"equipped":[63],"techniques":[65],"such":[66],"as":[67],"spectral":[68],"centroids,":[69],"group":[70],"delay":[71],"function,":[72],"integrated":[74],"noise":[75],"suppression":[76],"provide":[77],"promising":[78],"alternatives":[79],"MFCCs":[81],"for":[82],"embeddings":[85],"extraction.Experimental":[86],"results":[87],"demonstrate":[88],"up":[89],"16.3%":[91],"(VoxCeleb)":[92],"25.1%":[94],"(SITW)":[95],"relative":[96],"decrease":[97],"in":[98],"equal":[99],"error":[100],"rate":[101],"(EER)":[102],"the":[104],"baseline.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}