{"id":"https://openalex.org/W4404103225","doi":"https://doi.org/10.1109/icasspw62465.2024.10740924","title":"How Phonemes Contribute to Deep Speaker Models?","display_name":"How Phonemes Contribute to Deep Speaker Models?","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4404103225","doi":"https://doi.org/10.1109/icasspw62465.2024.10740924"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10740924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10740924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5039566915","display_name":"Pengqi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengqi Li","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100610983","display_name":"Tianhao Wang","orcid":"https://orcid.org/0000-0002-2126-6110"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075133420","display_name":"Askar Hamdulla","orcid":"https://orcid.org/0000-0002-2321-308X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Askar Hamdulla","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,China","institution_ids":["https://openalex.org/I96908189"]}]},{"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":["Tsinghua University,Center for Speech and Language Technologies,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Center for Speech and Language Technologies,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039566915"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":1.0911,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82071936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"838","last_page":"842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937999844551086,"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":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722245454788208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6025264263153076},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4161595106124878},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4041541814804077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40137752890586853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722245454788208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6025264263153076},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4161595106124878},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4041541814804077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40137752890586853}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10740924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10740924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"Which":[0],"phonemes":[1,45,75],"convey":[2],"more":[3,35,47,123],"speaker":[4,20,81,148],"traits":[5],"is":[6,54,154,164,168],"a":[7,68,150,162],"longstanding":[8],"question,":[9],"and":[10,30,88,107],"various":[11],"perception":[12,41,130],"experiments":[13],"were":[14,23],"conducted":[15,24,99],"with":[16,25,39,49,76,142],"human":[17,129],"subjects.":[18],"For":[19],"recognition,":[21],"studies":[22],"the":[26,31,40,59,62,72,92,100,118,128,136,147],"conventional":[27],"statistical":[28],"models":[29,53,82],"drawn":[32],"conclusions":[33],"are":[34,46,84,122,134],"or":[36,166],"less":[37],"consistent":[38],"results.":[42],"However,":[43,132],"which":[44,140],"important":[48,124,165],"modern":[50],"deep":[51,80],"neural":[52],"still":[55],"unexplored,":[56],"due":[57],"to":[58],"opaqueness":[60],"of":[61,74,79,94],"decision":[63],"process.":[64],"This":[65],"paper":[66],"conducts":[67],"novel":[69],"study":[70,101],"for":[71],"attribution":[73],"two":[77,103],"types":[78],"that":[83,160],"based":[85],"on":[86],"TDNN":[87],"CNN":[89],"respectively,":[90],"from":[91],"perspective":[93],"model":[95],"explanation.":[96],"Specifically,":[97],"we":[98],"by":[102],"post-explanation":[104],"methods:":[105],"LayerCAM":[106],"Time":[108],"Align":[109],"Occlusion":[110],"(TAO).":[111],"Experimental":[112],"results":[113],"showed":[114],"that:":[115],"(1)":[116],"At":[117,146],"population":[119],"level,":[120,149],"vowels":[121],"than":[125],"consonants,":[126],"confirming":[127],"studies.":[131,144],"fricatives":[133],"among":[135],"most":[137],"unimportant":[138],"phonemes,":[139],"contrasts":[141],"previous":[143],"(2)":[145],"large":[151],"between-speaker":[152],"variation":[153],"observed":[155],"regarding":[156],"phoneme":[157,163],"importance,":[158],"indicating":[159],"whether":[161],"not":[167],"largely":[169],"speaker-dependent.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}