{"id":"https://openalex.org/W3157804362","doi":"https://doi.org/10.21437/interspeech.2021-1889","title":"Restoring Degraded Speech via a Modified Diffusion Model","display_name":"Restoring Degraded Speech via a Modified Diffusion Model","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3157804362","doi":"https://doi.org/10.21437/interspeech.2021-1889","mag":"3157804362"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1889","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.11347","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100326952","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0001-6419-2038"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["Arizona State University"],"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043608888","display_name":"Suren Jayasuriya","orcid":"https://orcid.org/0000-0001-7143-4429"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suren Jayasuriya","raw_affiliation_strings":["Arizona State University"],"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021646973","display_name":"Visar Berisha","orcid":"https://orcid.org/0000-0001-8804-8874"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Visar Berisha","raw_affiliation_strings":["Arizona State University"],"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100326952"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":1.9807,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86869506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"221","last_page":"225"},"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":0.7918990254402161},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.7560749053955078},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7462659478187561},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6189844608306885},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.46424803137779236},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46229976415634155},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.45150530338287354},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42846623063087463},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41932305693626404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35077011585235596},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13634029030799866},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08029186725616455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918990254402161},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7560749053955078},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7462659478187561},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6189844608306885},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.46424803137779236},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46229976415634155},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.45150530338287354},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42846623063087463},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41932305693626404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35077011585235596},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13634029030799866},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08029186725616455},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-1889","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.11347","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.11347","pdf_url":"https://arxiv.org/pdf/2104.11347","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.11347","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.11347","pdf_url":"https://arxiv.org/pdf/2104.11347","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W2015069270","https://openalex.org/W2102950268","https://openalex.org/W2144404214","https://openalex.org/W2519091744","https://openalex.org/W2600556233","https://openalex.org/W2937525188","https://openalex.org/W2949382160","https://openalex.org/W2963091184","https://openalex.org/W2963341071","https://openalex.org/W2993118648","https://openalex.org/W2998616931","https://openalex.org/W3020389402","https://openalex.org/W3030437843","https://openalex.org/W3034771406","https://openalex.org/W3035068567","https://openalex.org/W3087665158","https://openalex.org/W3096159803","https://openalex.org/W3096992656","https://openalex.org/W3129651364","https://openalex.org/W3158243217","https://openalex.org/W3159973907"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W2281134365","https://openalex.org/W3211091508","https://openalex.org/W72660888","https://openalex.org/W2053531689","https://openalex.org/W1842536210"],"abstract_inverted_index":{"There":[0],"are":[1,183],"many":[2],"deterministic":[3],"mathematical":[4],"operations":[5],"(e.g.":[6],"compression,":[7,154,156],"clipping,":[8],"downsampling)":[9],"that":[10,32,88],"degrade":[11],"speech":[12,38,50,84,100,107,133,150],"quality":[13,51,134,148],"considerably.":[14],"In":[15],"this":[16],"paper":[17],"we":[18],"introduce":[19],"a":[20,26,41,60,73,187],"neural":[21],"network":[22],"architecture,":[23,165],"based":[24],"on":[25,104,140,171],"modification":[27],"of":[28,63,89,124,149],"the":[29,36,67,82,90,98,105,111,119,125,147,162],"DiffWave":[30,71,136,164],"model,":[31],"aims":[33],"to":[34,80,86,161],"restore":[35],"original":[37,91,99,126,163],"signal.":[39],"DiffWave,":[40],"recently":[42],"published":[43],"diffusion-based":[44],"vocoder,":[45],"has":[46],"shown":[47],"state-of-the-art":[48],"synthesized":[49],"and":[52,118,157,176],"relatively":[53],"shorter":[54],"waveform":[55],"generation":[56],"times,":[57],"with":[58,72],"only":[59,110],"small":[61],"set":[62],"parameters.":[64],"We":[65],"replace":[66],"mel-spectrum":[68,85,113],"upsampler":[69],"in":[70,131,177,186],"deep":[74],"CNN":[75],"upsampler,":[76],"which":[77],"is":[78,95,114],"trained":[79,96],"alter":[81],"degraded":[83,106,112,151],"match":[87],"speech.":[92,127],"The":[93],"model":[94,120,129,137],"using":[97],"waveform,":[101],"but":[102],"conditioned":[103],"mel-spectrum.":[108],"Post-training,":[109],"used":[115],"as":[116,138],"input":[117],"generates":[121],"an":[122],"estimate":[123],"Our":[128],"results":[130],"improved":[132],"(original":[135],"baseline)":[139],"several":[141,172],"different":[142],"experiments.":[143],"These":[144],"include":[145],"improving":[146],"by":[152],"LPC-10":[153],"AMR-NB":[155],"signal":[158],"clipping.":[159],"Compared":[160],"our":[166],"scheme":[167],"achieves":[168],"better":[169],"performance":[170],"objective":[173],"perceptual":[174],"metrics":[175],"subjective":[178],"comparisons.":[179],"Improvements":[180],"over":[181],"baseline":[182],"further":[184],"amplified":[185],"out-of-corpus":[188],"evaluation":[189],"setting.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}