{"id":"https://openalex.org/W3015644200","doi":"https://doi.org/10.1109/icassp40776.2020.9054204","title":"Wawenets: A No-Reference Convolutional Waveform-Based Approach to Estimating Narrowband and Wideband Speech Quality","display_name":"Wawenets: A No-Reference Convolutional Waveform-Based Approach to Estimating Narrowband and Wideband Speech Quality","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015644200","doi":"https://doi.org/10.1109/icassp40776.2020.9054204","mag":"3015644200"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5054842192","display_name":"Andrew Catellier","orcid":"https://orcid.org/0000-0002-5850-555X"},"institutions":[{"id":"https://openalex.org/I4210100297","display_name":"Institute for Telecommunication Sciences","ror":"https://ror.org/00mj5bc69","country_code":"US","type":"government","lineage":["https://openalex.org/I1343035065","https://openalex.org/I4210100297","https://openalex.org/I4387155216"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew A. Catellier","raw_affiliation_strings":["Institute for Telecommunication Sciences, Boulder, Colorado, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Telecommunication Sciences, Boulder, Colorado, USA","institution_ids":["https://openalex.org/I4210100297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044688661","display_name":"Stephen Voran","orcid":"https://orcid.org/0000-0001-7840-8848"},"institutions":[{"id":"https://openalex.org/I4210100297","display_name":"Institute for Telecommunication Sciences","ror":"https://ror.org/00mj5bc69","country_code":"US","type":"government","lineage":["https://openalex.org/I1343035065","https://openalex.org/I4210100297","https://openalex.org/I4387155216"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen D. Voran","raw_affiliation_strings":["Institute for Telecommunication Sciences, Boulder, Colorado, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Telecommunication Sciences, Boulder, Colorado, USA","institution_ids":["https://openalex.org/I4210100297"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054842192"],"corresponding_institution_ids":["https://openalex.org/I4210100297"],"apc_list":null,"apc_paid":null,"fwci":5.1522,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.96477946,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9987000226974487,"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":0.745867908000946},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.713402509689331},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.6663112640380859},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.6557998657226562},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6556755900382996},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6386094689369202},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6177576780319214},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.5719659924507141},{"id":"https://openalex.org/keywords/wideband-audio","display_name":"Wideband audio","score":0.5581179261207581},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5155251026153564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3569970726966858},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.3158652186393738},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.28781789541244507},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10592693090438843},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1001964807510376},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0871952474117279},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07813507318496704},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.07794132828712463},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.07041722536087036},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0681087076663971}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745867908000946},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.713402509689331},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.6663112640380859},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.6557998657226562},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6556755900382996},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6386094689369202},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6177576780319214},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.5719659924507141},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.5581179261207581},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5155251026153564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3569970726966858},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3158652186393738},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.28781789541244507},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10592693090438843},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1001964807510376},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0871952474117279},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07813507318496704},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.07794132828712463},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.07041722536087036},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0681087076663971},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2105921478","https://openalex.org/W2108708552","https://openalex.org/W2140651276","https://openalex.org/W2141998673","https://openalex.org/W2250357346","https://openalex.org/W2284628133","https://openalex.org/W2561217444","https://openalex.org/W2765278963","https://openalex.org/W2778517680","https://openalex.org/W2888722336","https://openalex.org/W2889830381","https://openalex.org/W2905783090","https://openalex.org/W2938881288","https://openalex.org/W2939156090","https://openalex.org/W2963403924","https://openalex.org/W2972419867","https://openalex.org/W2972598433","https://openalex.org/W2973403216","https://openalex.org/W2987307811","https://openalex.org/W3127686677","https://openalex.org/W6691509046","https://openalex.org/W6695553435","https://openalex.org/W6757561569","https://openalex.org/W6767534469","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W2140646420","https://openalex.org/W3016109656","https://openalex.org/W2342810974","https://openalex.org/W2058482658","https://openalex.org/W2017913521","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W2137927185","https://openalex.org/W3135613579","https://openalex.org/W2037635165"],"abstract_inverted_index":{"Building":[0],"on":[1,64],"prior":[2],"work":[3],"we":[4],"have":[5],"developed":[6],"a":[7,93],"no-reference":[8],"(NR)":[9],"waveform-based":[10],"convolutional":[11],"neural":[12],"network":[13],"(CNN)":[14],"architecture":[15],"that":[16,111],"can":[17],"accurately":[18],"estimate":[19],"speech":[20,28,69,117],"quality":[21,55],"or":[22,36],"intelligibility":[23,57],"of":[24,68,82],"narrowband":[25],"and":[26,56,119],"wideband":[27],"segments.":[29],"These":[30],"Wideband":[31],"Audio":[32],"Waveform":[33],"Evaluation":[34],"Networks,":[35],"WAWEnets,":[37],"achieve":[38],"very":[39],"high":[40],"per-speech-segment":[41],"correlation":[42],"(\u03c1":[43],"<sub":[44],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[45],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">seg</sub>":[46],"\u2265":[47],"0.92,":[48],"RMSE":[49],"\u2264":[50],"0.38)":[51],"to":[52,122],"established":[53],"full-reference":[54,105],"estimators":[58],"(PESQ,":[59],"POLQA,":[60],"PEMO,":[61],"STOI)":[62],"based":[63],"over":[65],"17":[66],"hours":[67],"from":[70],"127":[71],"previously":[72],"unseen":[73],"talkers":[74],"speaking":[75],"in":[76],"13":[77],"different":[78],"languages;":[79],"just":[80],"10%":[81],"our":[83],"total":[84],"data.":[85],"NR":[86,125],"correlations":[87],"at":[88],"this":[89],"level":[90],"across":[91],"such":[92],"broad":[94],"scope":[95],"are":[96],"unprecedented.":[97],"This":[98],"achievement":[99],"was":[100],"made":[101],"possible":[102],"by":[103],"using":[104],"estimates":[106],"as":[107],"training":[108],"targets":[109],"so":[110],"WAWEnets":[112],"could":[113],"learn":[114],"implicit":[115],"undistorted":[116],"models":[118],"exploit":[120],"them":[121],"produce":[123],"accurate":[124],"estimates.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}