{"id":"https://openalex.org/W4415133625","doi":"https://doi.org/10.21437/interspeech.2025-481","title":"On the Language and Gender Biases in PSTN, VoIP and Neural Audio Codecs","display_name":"On the Language and Gender Biases in PSTN, VoIP and Neural Audio Codecs","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415133625","doi":"https://doi.org/10.21437/interspeech.2025-481"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-481","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.02545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069779706","display_name":"Kemal Altwlkany","orcid":"https://orcid.org/0000-0002-7313-2800"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kemal Altwlkany","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114633381","display_name":"Amar Kuri\u0107","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amar Kuric","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114633382","display_name":"Emanuel Lacic","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emanuel Lacic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2896,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81094837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1348","last_page":"1352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.983299970626831,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.983299970626831,"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/codec","display_name":"Codec","score":0.6614999771118164},{"id":"https://openalex.org/keywords/transcoding","display_name":"Transcoding","score":0.5586000084877014},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5139999985694885},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.47350001335144043},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/voice-over-ip","display_name":"Voice over IP","score":0.3926999866962433},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3321000039577484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7285000085830688},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6614999771118164},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6017000079154968},{"id":"https://openalex.org/C134535813","wikidata":"https://www.wikidata.org/wiki/Q1888734","display_name":"Transcoding","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C171246234","wikidata":"https://www.wikidata.org/wiki/Q81945","display_name":"Voice over IP","level":3,"score":0.3926999866962433},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.328900009393692},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C105964291","wikidata":"https://www.wikidata.org/wiki/Q856184","display_name":"Code-excited linear prediction","level":4,"score":0.27320000529289246},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.2565999925136566}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-481","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.02545","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.02545","pdf_url":"https://arxiv.org/pdf/2506.02545","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.02545","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.02545","pdf_url":"https://arxiv.org/pdf/2506.02545","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415133625.pdf","grobid_xml":"https://content.openalex.org/works/W4415133625.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,83],"recent":[1],"years,":[2],"there":[3],"has":[4],"been":[5],"a":[6,117],"growing":[7],"focus":[8],"on":[9],"fairness":[10],"and":[11,24,71,96,124,139],"inclusivity":[12],"within":[13],"speech":[14,22,25,105],"technology,":[15],"particularly":[16],"in":[17,39,47,53,135],"areas":[18],"such":[19],"as":[20,35],"automatic":[21],"recognition":[23],"sentiment":[26],"analysis.":[27],"When":[28],"audio":[29,78,100,112],"is":[30,36,75],"transcoded":[31],"prior":[32],"to":[33,94],"processing,":[34],"the":[37,48,89,104],"case":[38],"streaming":[40],"or":[41],"real-time":[42],"applications,":[43],"any":[44],"inherent":[45],"bias":[46],"coding":[49,79],"mechanism":[50],"may":[51],"result":[52],"disparities.":[54],"This":[55],"not":[56],"only":[57],"affects":[58],"user":[59],"experience":[60],"but":[61],"can":[62],"also":[63],"have":[64],"broader":[65],"societal":[66],"implications":[67],"by":[68],"perpetuating":[69],"stereotypes":[70],"exclusion.":[72],"Thus,":[73],"it":[74],"important":[76],"that":[77,129,140],"mechanisms":[80],"are":[81,132],"unbiased.":[82],"this":[84],"work,":[85],"we":[86],"contribute":[87],"towards":[88],"scarce":[90],"research":[91],"with":[92],"respect":[93],"language":[95,144],"gender":[97,138],"biases":[98],"of":[99,107,120,137],"codecs.":[101],"By":[102],"analyzing":[103],"quality":[106],"over":[108],"2":[109],"million":[110],"multilingual":[111],"files":[113],"after":[114],"transcoding":[115],"through":[116],"representative":[118],"subset":[119],"codecs":[121,131,142],"(PSTN,":[122],"VoIP":[123],"neural),":[125],"our":[126],"results":[127],"indicate":[128],"PSTN":[130],"strongly":[133],"biased":[134],"terms":[136],"neural":[141],"introduce":[143],"biases.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-14T00:00:00"}