{"id":"https://openalex.org/W4372347392","doi":"https://doi.org/10.1109/icassp49357.2023.10095850","title":"SRTNET: Time Domain Speech Enhancement via Stochastic Refinement","display_name":"SRTNET: Time Domain Speech Enhancement via Stochastic Refinement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372347392","doi":"https://doi.org/10.1109/icassp49357.2023.10095850"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095850","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/A5060486114","display_name":"Zhibin Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhibin Qiu","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000920886","display_name":"Mengfan Fu","orcid":"https://orcid.org/0000-0002-2854-6617"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengfan Fu","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062830446","display_name":"Yinfeng Yu","orcid":"https://orcid.org/0000-0003-3089-4140"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinfeng Yu","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China","Department of Computer Science and Technology, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005931624","display_name":"Lili Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lili Yin","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055546056","display_name":"Fuchun Sun","orcid":"https://orcid.org/0000-0003-3546-6305"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchun Sun","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,China","Department of Computer Science and Technology, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China","Xinjiang Key Laboratory of Multi-lingual Information Technology, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Multi-lingual Information Technology, Urumqi, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5060486114"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":4.1352,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95175072,"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":"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.8122566938400269},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6956666111946106},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5454488396644592},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5186278223991394},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48948514461517334},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4556678831577301},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.44676318764686584},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.43358469009399414},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.42211073637008667},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34536871314048767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32359468936920166},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12680372595787048},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10868388414382935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10627138614654541},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09365281462669373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8122566938400269},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6956666111946106},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5454488396644592},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5186278223991394},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48948514461517334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4556678831577301},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.44676318764686584},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.43358469009399414},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.42211073637008667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34536871314048767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32359468936920166},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12680372595787048},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10868388414382935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10627138614654541},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09365281462669373},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095850","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2015069270","https://openalex.org/W2070126272","https://openalex.org/W2094721231","https://openalex.org/W2144404214","https://openalex.org/W2559260703","https://openalex.org/W2766672686","https://openalex.org/W2802304149","https://openalex.org/W2804078698","https://openalex.org/W2883322837","https://openalex.org/W2901552243","https://openalex.org/W2911579794","https://openalex.org/W2940177920","https://openalex.org/W2949558265","https://openalex.org/W2952218014","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2998832642","https://openalex.org/W3005621653","https://openalex.org/W3011982609","https://openalex.org/W3015411705","https://openalex.org/W3016056257","https://openalex.org/W3036167779","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3102190437","https://openalex.org/W3109018774","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3137758952","https://openalex.org/W3160324929","https://openalex.org/W3184410885","https://openalex.org/W4221144097","https://openalex.org/W4232282348","https://openalex.org/W4312756164","https://openalex.org/W6752378368","https://openalex.org/W6756162338","https://openalex.org/W6762114000","https://openalex.org/W6776095078","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6798721538"],"related_works":["https://openalex.org/W1630865680","https://openalex.org/W4214692512","https://openalex.org/W2373767407","https://openalex.org/W2516933085","https://openalex.org/W3168109306","https://openalex.org/W2358461432","https://openalex.org/W3176700874","https://openalex.org/W2089240210","https://openalex.org/W2653598178","https://openalex.org/W3081644756"],"abstract_inverted_index":{"Diffusion":[0],"model,":[1],"as":[2,31],"a":[3,32,40,57,62,66],"new":[4],"generative":[5],"model":[6,30],"which":[7,69],"is":[8,17,99],"very":[9],"popular":[10],"in":[11,20,49],"image":[12],"generation":[13],"and":[14,65,83,94],"audio":[15],"synthesis,":[16],"rarely":[18],"used":[19],"speech":[21,44],"enhancement.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,55],"use":[27],"the":[28,72,78],"diffusion":[29],"module":[33,64],"for":[34,43],"stochastic":[35,67],"refinement.":[36],"We":[37,75],"propose":[38],"SRTNet,":[39],"novel":[41],"method":[42,82,88],"enhancement":[45],"via":[46],"Stochastic":[47],"Refinement":[48],"complete":[50],"Time":[51],"b":[52],"domain.":[53],"Specifically,":[54],"design":[56],"joint":[58],"network":[59],"consisting":[60],"of":[61,80],"deterministic":[63],"module,":[68],"makes":[70],"up":[71],"\"enhance-and-refine\"":[73],"paradigm.":[74],"theoretically":[76],"demonstrate":[77],"feasibility":[79],"our":[81,87],"experimentally":[84],"prove":[85],"that":[86],"achieves":[89],"faster":[90,92],"training,":[91],"sampling":[93],"higher":[95],"quality.":[96],"Our":[97],"code":[98],"available":[100],"at":[101],"https://github.com/zhibinQiu/SRTNet.git":[102]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
