{"id":"https://openalex.org/W4372347394","doi":"https://doi.org/10.1109/icassp49357.2023.10094773","title":"TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement","display_name":"TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372347394","doi":"https://doi.org/10.1109/icassp49357.2023.10094773"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5045674158","display_name":"Yunyang Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunyang Zeng","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042073320","display_name":"Joseph Konan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Konan","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013398230","display_name":"Shuo Han","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo Han","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046503917","display_name":"David Bick","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Bick","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012381843","display_name":"Muqiao Yang","orcid":"https://orcid.org/0000-0001-6273-0138"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muqiao Yang","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Meta Reality Labs Research"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I91044093","display_name":"Zayed University","ror":"https://ror.org/03snqfa66","country_code":"AE","type":"education","lineage":["https://openalex.org/I91044093"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Carnegie Mellon University","Mohammed Bin Zayed University of AI"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Mohammed Bin Zayed University of AI","institution_ids":["https://openalex.org/I91044093"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5045674158"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.4232,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81704951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.7384338974952698},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.682373046875},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5642940402030945},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.53504478931427},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4983818531036377},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4485458731651306},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3603905737400055},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32020676136016846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32006561756134033},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14277133345603943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14261162281036377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384338974952698},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.682373046875},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5642940402030945},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.53504478931427},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4983818531036377},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4485458731651306},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3603905737400055},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32020676136016846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32006561756134033},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14277133345603943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14261162281036377},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5099999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1587932887","https://openalex.org/W1897240248","https://openalex.org/W1999405202","https://openalex.org/W2013374607","https://openalex.org/W2040669471","https://openalex.org/W2043701535","https://openalex.org/W2058094241","https://openalex.org/W2085662862","https://openalex.org/W2132710264","https://openalex.org/W2291877678","https://openalex.org/W2593116425","https://openalex.org/W2610961739","https://openalex.org/W2696558042","https://openalex.org/W2892110446","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2972443522","https://openalex.org/W2973133192","https://openalex.org/W3030102521","https://openalex.org/W3097934054","https://openalex.org/W3097945073","https://openalex.org/W3160085755","https://openalex.org/W3163827866","https://openalex.org/W3197284240","https://openalex.org/W3197912330","https://openalex.org/W3200245256","https://openalex.org/W4200634567","https://openalex.org/W4225302959","https://openalex.org/W4253928870","https://openalex.org/W4286850942","https://openalex.org/W4296070384","https://openalex.org/W4297841912","https://openalex.org/W6778247133","https://openalex.org/W6801588699","https://openalex.org/W6804711698","https://openalex.org/W6805434863"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W2738829087","https://openalex.org/W2231565466","https://openalex.org/W3043214604","https://openalex.org/W1505346162","https://openalex.org/W2120771489","https://openalex.org/W2051376034"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,109,122],"models":[2,146,150],"have":[3],"greatly":[4],"progressed":[5],"in":[6,13,42,108,120],"recent":[7],"years,":[8],"but":[9],"still":[10],"show":[11,112],"limits":[12],"perceptual":[14,25,127],"quality":[15,26,128],"of":[16,59,89,103],"their":[17],"speech":[18,35,106,121,124],"outputs.":[19],"We":[20,51,111,131],"propose":[21],"an":[22,39,117],"objective":[23,119],"for":[24,56],"based":[27],"on":[28],"temporal":[29,74,93],"acoustic":[30,61,83,90,94],"parameters.":[31],"These":[32],"are":[33],"fundamental":[34],"features":[36],"that":[37,79,113,143],"play":[38],"essential":[40],"role":[41],"various":[43],"applications,":[44],"including":[45],"speaker":[46],"recognition":[47],"and":[48,73,101,129,147],"paralinguistic":[49],"analysis.":[50],"provide":[52],"a":[53,86],"differentiable":[54],"estimator":[55],"four":[57],"categories":[58,88],"low-level":[60],"descriptors":[62],"involving:":[63],"frequency-related":[64],"parameters,":[65,69,72,91],"energy":[66],"or":[67,85],"amplitude-related":[68],"spectral":[70],"balance":[71],"features.":[75],"Un-like":[76],"prior":[77],"work":[78],"looks":[80],"at":[81],"aggregated":[82],"parameters":[84],"few":[87],"our":[92,154],"parameter":[95],"(TAP)":[96],"loss":[97],"enables":[98],"auxiliary":[99,118],"optimization":[100],"improvement":[102],"many":[104],"fine-grained":[105],"characteristics":[107],"workflows.":[110],"adding":[114],"TAPLoss":[115],"as":[116],"produces":[123],"with":[125],"improved":[126],"intelligibility.":[130],"use":[132],"data":[133],"from":[134,153],"the":[135],"Deep":[136],"Noise":[137],"Suppression":[138],"2020":[139],"Challenge":[140],"to":[141],"demonstrate":[142],"both":[144],"time-domain":[145],"time-frequency":[148],"domain":[149],"can":[151],"benefit":[152],"method.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}