{"id":"https://openalex.org/W4372260337","doi":"https://doi.org/10.1109/icassp49357.2023.10096680","title":"Torchaudio-Squim: Reference-Less Speech Quality and Intelligibility Measures in Torchaudio","display_name":"Torchaudio-Squim: Reference-Less Speech Quality and Intelligibility Measures in Torchaudio","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260337","doi":"https://doi.org/10.1109/icassp49357.2023.10096680"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096680","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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075227645","display_name":"Ke Tan","orcid":null},"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":"Ke Tan","raw_affiliation_strings":["Meta Reality Labs Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031088292","display_name":"Zhaoheng Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoheng Ni","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075510192","display_name":"Pranay Manocha","orcid":"https://orcid.org/0000-0003-3284-5908"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranay Manocha","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067937592","display_name":"Xiaohui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070756529","display_name":"Ethan Henderson","orcid":"https://orcid.org/0000-0002-2203-7838"},"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":"Ethan Henderson","raw_affiliation_strings":["Meta Reality Labs Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"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":"Buye Xu","raw_affiliation_strings":["Meta Reality Labs Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.2381,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.98718584,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8361313343048096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8151713013648987},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7768939733505249},{"id":"https://openalex.org/keywords/unavailability","display_name":"Unavailability","score":0.6759254336357117},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6333276629447937},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5831727385520935},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5160369873046875},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4748694598674774},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46671077609062195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45020052790641785},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40170180797576904},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.3720775246620178},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32520949840545654},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.09744429588317871},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07304716110229492}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8361313343048096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151713013648987},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7768939733505249},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.6759254336357117},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6333276629447937},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5831727385520935},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5160369873046875},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4748694598674774},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46671077609062195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45020052790641785},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40170180797576904},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3720775246620178},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32520949840545654},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.09744429588317871},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07304716110229492},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096680","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","score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2141998673","https://openalex.org/W2157600120","https://openalex.org/W2557915412","https://openalex.org/W2799258971","https://openalex.org/W2963403924","https://openalex.org/W2972394484","https://openalex.org/W2990118552","https://openalex.org/W2991361823","https://openalex.org/W3015199127","https://openalex.org/W3015545615","https://openalex.org/W3015644200","https://openalex.org/W3097906045","https://openalex.org/W3105857760","https://openalex.org/W3161364427","https://openalex.org/W3161480375","https://openalex.org/W3196475561","https://openalex.org/W3198102247","https://openalex.org/W3200245256","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W3208743843","https://openalex.org/W4225302959","https://openalex.org/W4296068974","https://openalex.org/W4297841766","https://openalex.org/W4311167834","https://openalex.org/W4361745739","https://openalex.org/W4385245566","https://openalex.org/W6611703090","https://openalex.org/W6729924827","https://openalex.org/W6739901393","https://openalex.org/W6761921182","https://openalex.org/W6770208069","https://openalex.org/W6770232298","https://openalex.org/W6775804823","https://openalex.org/W6785906987","https://openalex.org/W6795684877","https://openalex.org/W6801588699","https://openalex.org/W6802584641","https://openalex.org/W6802816715"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2342810974","https://openalex.org/W2058482658","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W4386746628","https://openalex.org/W2037635165"],"abstract_inverted_index":{"Measuring":[0],"quality":[1,28],"and":[2,29,43,70,88,101,108,113,127,165,184],"intelligibility":[3,30],"of":[4,15,24,46,97,162,169],"a":[5,10,22,44,120,129,141],"speech":[6,16,71,153,157,164,181],"signal":[7],"is":[8,145],"usually":[9],"critical":[11],"step":[12],"in":[13,62,93,140,172],"development":[14],"processing":[17,72,182],"systems.":[18],"To":[19],"enable":[20],"this,":[21],"variety":[23],"metrics":[25,52,112],"to":[26,48,82],"measure":[27],"under":[31],"different":[32],"assumptions":[33],"have":[34],"been":[35],"developed.":[36],"Through":[37],"this":[38],"paper,":[39],"we":[40,99],"introduce":[41],"tools":[42,177],"set":[45],"models":[47,58,103,138],"estimate":[49],"such":[50,175],"known":[51],"using":[53],"deep":[54,77],"neural":[55],"networks.":[56],"These":[57,137],"are":[59],"made":[60],"available":[61],"the":[63,67,75,94,150,160,166],"well-established":[64],"TorchAudio":[65],"library,":[66],"core":[68],"audio":[69],"library":[73],"within":[74],"PyTorch":[76],"learning":[78],"framework.":[79],"We":[80,118],"refer":[81],"it":[83],"as":[84,154],"TorchAudio-Squim,":[85],"TorchAudio-Speech":[86],"QUality":[87],"Intelligibility":[89],"Measures.":[90],"More":[91],"specifically,":[92],"current":[95],"version":[96],"TorchAudio-squim,":[98],"establish":[100],"release":[102],"for":[104,123,133,156],"estimating":[105],"PESQ,":[106],"STOI":[107],"SI-SDR":[109],"among":[110,115],"objective":[111,124],"MOS":[114],"subjective":[116,134,170],"metrics.":[117],"develop":[119],"novel":[121],"approach":[122,132],"metric":[125,135],"estimation":[126],"use":[128],"recently":[130],"developed":[131],"estimation.":[136],"operate":[139],"\"referenceless\"":[142],"manner,":[143],"that":[144],"they":[146],"do":[147],"not":[148],"require":[149],"corresponding":[151],"clean":[152,163],"reference":[155],"assessment.":[158],"Given":[159],"unavailability":[161],"effortful":[167],"process":[168],"evaluation":[171],"real-world":[173],"situations,":[174],"easy-to-use":[176],"would":[178],"greatly":[179],"benefit":[180],"research":[183],"development.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}