{"id":"https://openalex.org/W4401609195","doi":"https://doi.org/10.1109/icasspw62465.2024.10627035","title":"Enhancing GAN-based Vocoders with Contrastive Learning Under Data-Limited Condition","display_name":"Enhancing GAN-based Vocoders with Contrastive Learning Under Data-Limited Condition","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609195","doi":"https://doi.org/10.1109/icasspw62465.2024.10627035"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627035","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/A5101836380","display_name":"Haoming Guo","orcid":"https://orcid.org/0000-0003-2900-8244"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haoming Guo","raw_affiliation_strings":["University of California,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007649701","display_name":"Seth Z. Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seth Z. Zhao","raw_affiliation_strings":["University of California,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038985725","display_name":"Jiachen Lian","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiachen Lian","raw_affiliation_strings":["University of California,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092897580","display_name":"Gopala Anumanchipalli","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopala Anumanchipalli","raw_affiliation_strings":["University of California,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["University of California,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101836380"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.7274,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75467015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"480","last_page":"484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9517999887466431,"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":0.9517999887466431,"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":0.9373000264167786,"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/computer-science","display_name":"Computer science","score":0.7064964771270752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39774033427238464},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3961174488067627}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064964771270752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39774033427238464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3961174488067627}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10627035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627035","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2107860279","https://openalex.org/W2842511635","https://openalex.org/W2954540134","https://openalex.org/W3035232877","https://openalex.org/W3092028330","https://openalex.org/W3099088591","https://openalex.org/W3162391496","https://openalex.org/W3166396011","https://openalex.org/W3171615848","https://openalex.org/W3183932535","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4212774754","https://openalex.org/W4221152299","https://openalex.org/W4221153068","https://openalex.org/W4225329057","https://openalex.org/W4280552695","https://openalex.org/W4281743943","https://openalex.org/W4285483774","https://openalex.org/W4286869901","https://openalex.org/W4297808394","https://openalex.org/W4297841354","https://openalex.org/W4298289240","https://openalex.org/W4312402389","https://openalex.org/W4385807463","https://openalex.org/W4391021811","https://openalex.org/W6765696844","https://openalex.org/W6767111847","https://openalex.org/W6770103389","https://openalex.org/W6779093361","https://openalex.org/W6780507278","https://openalex.org/W6783867762","https://openalex.org/W6788742436","https://openalex.org/W6791353385","https://openalex.org/W6803132585","https://openalex.org/W6810057765","https://openalex.org/W6810168380","https://openalex.org/W6838843145","https://openalex.org/W6838853235","https://openalex.org/W6840200333","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Vocoder":[0],"models":[1,27],"have":[2],"recently":[3],"achieved":[4],"substantial":[5],"progress":[6],"in":[7,44,127],"generating":[8],"authentic":[9],"audio":[10,30],"comparable":[11],"to":[12,48,73,90,93],"human":[13],"quality":[14,52,77],"while":[15],"significantly":[16],"reducing":[17],"memory":[18],"requirement":[19],"and":[20,101],"inference":[21],"time.":[22],"However,":[23],"these":[24],"data-hungry":[25],"generative":[26],"require":[28],"large-scale":[29],"data":[31],"for":[32],"learning":[33,42,72],"good":[34],"representations.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"apply":[40],"contrastive":[41,71],"methods":[43],"training":[45,115],"the":[46,50,54,75,79,88,95,99,103,109,121],"vocoder":[47,55,80],"improve":[49,94,123],"perceptual":[51],"of":[53,78,98],"without":[56],"modifying":[57],"its":[58],"architecture":[59],"or":[60],"adding":[61],"more":[62],"data.":[63],"We":[64,85,107],"design":[65],"an":[66],"auxiliary":[67],"task":[68,89,111],"with":[69,113],"mel-spectrogram":[70],"enhance":[74],"utterance-level":[76],"model":[81,100,124],"under":[82],"data-limited":[83,128],"conditions.":[84],"also":[86],"extend":[87],"include":[91],"waveforms":[92],"multi-modality":[96],"comprehension":[97],"address":[102],"discriminator":[104],"overfitting":[105],"problem.":[106],"optimize":[108],"additional":[110],"simultaneously":[112],"GAN":[114],"objectives.":[116],"Our":[117],"results":[118],"show":[119],"that":[120],"tasks":[122],"performance":[125],"substantially":[126],"settings.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}