{"id":"https://openalex.org/W4297841623","doi":"https://doi.org/10.21437/interspeech.2022-763","title":"DENT-DDSP: Data-efficient noisy speech generator using differentiable digital signal processors for explicit distortion modelling and noise-robust speech recognition","display_name":"DENT-DDSP: Data-efficient noisy speech generator using differentiable digital signal processors for explicit distortion modelling and noise-robust speech recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841623","doi":"https://doi.org/10.21437/interspeech.2022-763"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-763","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-763","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5041055222","display_name":"Zixun Guo","orcid":"https://orcid.org/0000-0002-7327-4382"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zixun Guo","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418547","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-1957-6432"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3799","last_page":"3803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/distortion","display_name":"Distortion (music)","score":0.7093300819396973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6801989674568176},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6438964605331421},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.636362612247467},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.59161376953125},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5305927991867065},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4755135178565979},{"id":"https://openalex.org/keywords/signal-generator","display_name":"Signal generator","score":0.45361071825027466},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4470778703689575},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4168478846549988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3127443790435791},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15538150072097778},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0862472653388977},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.08256924152374268},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08211717009544373},{"id":"https://openalex.org/keywords/amplifier","display_name":"Amplifier","score":0.07259133458137512},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06354957818984985}],"concepts":[{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.7093300819396973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6801989674568176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6438964605331421},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.636362612247467},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.59161376953125},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5305927991867065},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4755135178565979},{"id":"https://openalex.org/C207912722","wikidata":"https://www.wikidata.org/wiki/Q1259123","display_name":"Signal generator","level":3,"score":0.45361071825027466},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4470778703689575},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4168478846549988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3127443790435791},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15538150072097778},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0862472653388977},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.08256924152374268},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08211717009544373},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.07259133458137512},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06354957818984985},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-763","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-763","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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":22,"referenced_works":["https://openalex.org/W105750483","https://openalex.org/W1573570773","https://openalex.org/W1831910457","https://openalex.org/W1872696642","https://openalex.org/W1992475611","https://openalex.org/W2104387568","https://openalex.org/W2166637769","https://openalex.org/W2250499536","https://openalex.org/W2311973309","https://openalex.org/W2891138528","https://openalex.org/W2899396049","https://openalex.org/W2972818416","https://openalex.org/W3000389243","https://openalex.org/W3011871163","https://openalex.org/W3095212898","https://openalex.org/W3097777922","https://openalex.org/W3137000704","https://openalex.org/W3195797672","https://openalex.org/W4221156109","https://openalex.org/W4223945715","https://openalex.org/W4297915175","https://openalex.org/W4385822727"],"related_works":["https://openalex.org/W1546240199","https://openalex.org/W193702574","https://openalex.org/W2084668538","https://openalex.org/W2063862874","https://openalex.org/W2154415461","https://openalex.org/W1923241916","https://openalex.org/W2151365363","https://openalex.org/W2798852438","https://openalex.org/W642007152","https://openalex.org/W254504168"],"abstract_inverted_index":{"The":[0],"performances":[1,170],"of":[2,82,110,180,186],"automatic":[3],"speech":[4],"recognition":[5],"(ASR)":[6],"systems":[7,26],"degrade":[8],"drastically":[9],"under":[10,27],"noisy":[11,34,94,130,164],"conditions.Explicit":[12],"distortion":[13,41],"modelling":[14],"(EDM),":[15],"as":[16],"a":[17,59,175],"feature":[18],"compensation":[19],"step,":[20],"is":[21,189],"able":[22,124],"to":[23,66,85,104,115,125,171],"enhance":[24],"ASR":[25,135,139],"such":[28],"conditions":[29],"by":[30,121],"simulating":[31],"the":[32,37,92,99,118,127,133,142,148,152,158,162,172,187],"in-domain":[33,129],"speeches":[35],"from":[36,96,166],"clean":[38],"counterparts.Yet,":[39],"existing":[40],"models":[42,107,140],"are":[43,123,145],"either":[44],"non-trainable":[45],"or":[46],"unexplainable":[47],"and":[48,52,62,77,151],"often":[49],"lack":[50],"controllability":[51],"generalization":[53],"ability.In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"fully":[60],"explainable":[61],"controllable":[63],"model:":[64],"DENT-DDSP":[65,97,122,167],"achieve":[67,86],"EDM.DENT-DDSP":[68],"utilizes":[69],"novel":[70],"differentiable":[71],"digital":[72],"signal":[73],"processing":[74],"(DDSP)":[75],"components":[76],"requires":[78],"only":[79],"10":[80],"seconds":[81],"training":[83],"data":[84,95,119,131,150,165],"high":[87],"fidelity.The":[88],"experiment":[89,155],"shows":[90,156],"that":[91,157],"simulated":[93,120,149,163],"achieves":[98,168],"highest":[100],"simulation":[101],"fidelity":[102],"compared":[103],"other":[105],"baseline":[106],"in":[108,132,178],"terms":[109,179],"multi-scale":[111],"spectral":[112],"loss":[113],"(MSSL).Moreover,":[114],"validate":[116],"whether":[117],"replace":[126],"scarce":[128],"noise-robust":[134],"tasks,":[136],"several":[137],"downstream":[138],"with":[141,161,174],"same":[143],"architecture":[144],"trained":[146,160],"using":[147],"real":[153],"data.The":[154],"model":[159,188],"similar":[169],"benchmark":[173],"2.7%":[176],"difference":[177],"word":[181],"error":[182],"rate":[183],"(WER).The":[184],"code":[185],"released":[190],"online":[191],"1":[192],".":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}