{"id":"https://openalex.org/W4406461432","doi":"https://doi.org/10.1109/slt61566.2024.10832147","title":"Diffusion-Based Generative Modeling With Discriminative Guidance for Streamable Speech Enhancement","display_name":"Diffusion-Based Generative Modeling With Discriminative Guidance for Streamable Speech Enhancement","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461432","doi":"https://doi.org/10.1109/slt61566.2024.10832147"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5027035775","display_name":"Chenda Li","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenda Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682990","display_name":"Samuele Cornell","orcid":"https://orcid.org/0000-0002-5358-1844"},"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":"Samuele Cornell","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"333","last_page":"340"},"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/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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8679685592651367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6769843101501465},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6480288505554199},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6171744465827942},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5864065289497375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5206417441368103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42513832449913025},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32087427377700806},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07903173565864563}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8679685592651367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769843101501465},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6480288505554199},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6171744465827942},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5864065289497375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5206417441368103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42513832449913025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32087427377700806},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07903173565864563},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.800000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1505878979","https://openalex.org/W1552314771","https://openalex.org/W1989337816","https://openalex.org/W1991111872","https://openalex.org/W2013035813","https://openalex.org/W2044893557","https://openalex.org/W2061698928","https://openalex.org/W2107860279","https://openalex.org/W2127851351","https://openalex.org/W2289394825","https://openalex.org/W2516001803","https://openalex.org/W2559260703","https://openalex.org/W2937484199","https://openalex.org/W2952218014","https://openalex.org/W2959300817","https://openalex.org/W2962866211","https://openalex.org/W2972436155","https://openalex.org/W2982471419","https://openalex.org/W3004970274","https://openalex.org/W3015199127","https://openalex.org/W3015312544","https://openalex.org/W3032514799","https://openalex.org/W3036167779","https://openalex.org/W3096408984","https://openalex.org/W3099330747","https://openalex.org/W3196475561","https://openalex.org/W3197832224","https://openalex.org/W3209490467","https://openalex.org/W4211127940","https://openalex.org/W4221144097","https://openalex.org/W4224938485","https://openalex.org/W4225302959","https://openalex.org/W4245919820","https://openalex.org/W4297841790","https://openalex.org/W4372266775","https://openalex.org/W4375869119","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4392908343","https://openalex.org/W4392939451","https://openalex.org/W6765775151","https://openalex.org/W6779823529","https://openalex.org/W6786375611","https://openalex.org/W6840373428"],"related_works":["https://openalex.org/W4396941953","https://openalex.org/W2093104230","https://openalex.org/W2987280934","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W3014948380","https://openalex.org/W4386184937","https://openalex.org/W4394728283"],"abstract_inverted_index":{"Diffusion-based":[0],"generative":[1,113,124],"models":[2,57],"(DGMs)":[3],"have":[4],"recently":[5],"attracted":[6],"attention":[7],"in":[8,33,58,105],"speech":[9],"enhancement":[10],"(SE)":[11],"research":[12],"as":[13],"previous":[14],"works":[15],"showed":[16],"a":[17,120],"remarkable":[18],"generalization":[19],"capability.":[20],"However,":[21],"DGMs":[22],"are":[23],"also":[24,87],"computationally":[25],"intensive,":[26],"since":[27],"they":[28],"usually":[29],"require":[30,68],"many":[31],"iterations":[32],"the":[34,59,63,74],"reverse":[35],"diffusion":[36],"process":[37],"(RDP),":[38],"making":[39],"them":[40],"impractical":[41],"for":[42,77,89],"streaming":[43],"SE":[44],"systems.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,118],"propose":[50,119],"to":[51,140],"use":[52],"scores":[53,67],"estimated":[54],"from":[55],"discriminative":[56,75,100,115],"first":[60],"steps":[61,102],"of":[62,99,130],"RDP.":[64],"These":[65],"discriminative-based":[66],"only":[69],"one":[70],"forward":[71],"pass":[72],"with":[73,109,126],"model":[76,108,125],"multiple":[78],"RDP":[79],"steps,":[80],"thus":[81],"greatly":[82],"reducing":[83],"computations.":[84],"This":[85],"approach":[86],"allows":[88],"performance":[90,111,137],"improvements.":[91],"We":[92],"show":[93],"that":[94],"choosing":[95],"an":[96,106,127],"appropriate":[97],"number":[98],"guidance":[101],"can":[103],"result":[104],"overall":[107],"better":[110],"than":[112],"and":[114],"models.":[116,142],"Furthermore,":[117],"novel":[121],"streamable":[122],"time-domain":[123],"algorithmic":[128],"latency":[129],"50":[131],"ms,":[132],"which":[133],"has":[134],"no":[135],"significant":[136],"degradation":[138],"compared":[139],"offline":[141]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}