{"id":"https://openalex.org/W4392904154","doi":"https://doi.org/10.1109/icassp48485.2024.10446998","title":"Discrete Audio Representation as an Alternative to Mel-Spectrograms for Speaker and Speech Recognition","display_name":"Discrete Audio Representation as an Alternative to Mel-Spectrograms for Speaker and Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904154","doi":"https://doi.org/10.1109/icassp48485.2024.10446998"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5069691915","display_name":"Krishna C. Puvvada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna C. Puvvada","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040007143","display_name":"Nithin Rao Koluguri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nithin Rao Koluguri","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073181369","display_name":"Kunal Dhawan","orcid":"https://orcid.org/0000-0002-5276-2475"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunal Dhawan","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747392","display_name":"Jagadeesh Balam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jagadeesh Balam","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12111","last_page":"12115"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/spectrogram","display_name":"Spectrogram","score":0.8781583309173584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8383560180664062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8169654607772827},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5760252475738525},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5553061962127686},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5215566158294678},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4587211608886719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40696877241134644},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31599730253219604}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8781583309173584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8383560180664062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8169654607772827},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5760252475738525},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5553061962127686},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5215566158294678},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4587211608886719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40696877241134644},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31599730253219604}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2622566932","https://openalex.org/W2808631503","https://openalex.org/W2936774411","https://openalex.org/W2963250244","https://openalex.org/W2969985801","https://openalex.org/W3030437843","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3205878676","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4226033575","https://openalex.org/W4292779060","https://openalex.org/W4307323391","https://openalex.org/W4311000453","https://openalex.org/W4313679638","https://openalex.org/W4318351475","https://openalex.org/W4320013820","https://openalex.org/W4323066695","https://openalex.org/W4323651091","https://openalex.org/W4378501656","https://openalex.org/W4380551955","https://openalex.org/W4381786045","https://openalex.org/W4381827575","https://openalex.org/W4384918448","https://openalex.org/W4391021542","https://openalex.org/W6678809451","https://openalex.org/W6711908931","https://openalex.org/W6770434673","https://openalex.org/W6771467084","https://openalex.org/W6778883912","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6849105126","https://openalex.org/W6850218400","https://openalex.org/W6850334629","https://openalex.org/W6853515095","https://openalex.org/W6853611000","https://openalex.org/W6853998256","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Discrete":[0],"audio":[1,4,24,49,70,91,127,165],"representation,":[2],"aka":[3],"tokenization,":[5],"has":[6],"seen":[7],"renewed":[8],"interest":[9],"driven":[10],"by":[11],"its":[12],"potential":[13],"to":[14,52,132,135],"facilitate":[15],"the":[16,45,87,104,158,178],"application":[17],"of":[18,47,99,141],"text":[19],"language":[20],"modeling":[21],"approaches":[22],"in":[23,123,143],"domain.":[25],"To":[26],"this":[27,64],"end,":[28],"various":[29,57],"compression":[30,68,131],"and":[31,59,78,107,145,156,181],"representation-learning":[32],"based":[33,69,164],"tokenization":[34],"schemes":[35],"have":[36],"been":[37],"proposed.":[38],"However,":[39],"there":[40],"is":[41,150],"limited":[42],"investigation":[43],"into":[44],"performance":[46,142],"compression-based":[48],"tokens":[50,71,92,128],"compared":[51,134],"well-established":[53],"mel-spectrogram":[54,100,136],"features":[55,101,137],"across":[56],"speaker":[58,124,146],"speech":[60,144],"related":[61,147],"tasks.":[62,125],"In":[63],"paper,":[65],"we":[66],"evaluate":[67],"on":[72,90,95],"three":[73],"tasks:":[74],"Speaker":[75],"Verification,":[76],"Diarization":[77],"(Multi-lingual)":[79],"Speech":[80],"Recognition.":[81],"Our":[82],"findings":[83],"indicate":[84],"that":[85],"(i)":[86],"models":[88,115],"trained":[89],"perform":[93],"competitively,":[94],"average":[96],"within":[97],"1%":[98],"for":[102,118,130,152,177,184],"all":[103],"tasks":[105],"considered,":[106],"do":[108],"not":[109],"surpass":[110],"them":[111],"yet.":[112],"(ii)":[113],"these":[114],"exhibit":[116],"robustness":[117],"out-of-domain":[119],"narrowband":[120],"data,":[121],"particularly":[122],"(iii)":[126],"allow":[129],"20x":[133],"with":[138],"minimal":[139],"loss":[140],"tasks,":[148],"which":[149],"crucial":[151],"low":[153],"bit-rate":[154],"applications,":[155],"(iv)":[157],"examined":[159],"Residual":[160],"Vector":[161],"Quantization":[162],"(RVQ)":[163],"tokenizer":[166,186],"exhibits":[167],"a":[168,174],"low-pass":[169],"frequency":[170],"response":[171],"characteristic,":[172],"offering":[173],"plausible":[175],"explanation":[176],"observed":[179],"results,":[180],"providing":[182],"insight":[183],"future":[185],"designs.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}