{"id":"https://openalex.org/W4225269836","doi":"https://doi.org/10.1109/icassp43922.2022.9746609","title":"A Time Domain Progressive Learning Approach with SNR Constriction for Single-Channel Speech Enhancement and Recognition","display_name":"A Time Domain Progressive Learning Approach with SNR Constriction for Single-Channel Speech Enhancement and Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225269836","doi":"https://doi.org/10.1109/icassp43922.2022.9746609"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746609","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5005376611","display_name":"Zhaoxu Nian","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoxu Nian","raw_affiliation_strings":["University of Science and Technology of China,Hefei,P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,Hefei,P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083831776","display_name":"Yu Ting Yeung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Ting Yeung","raw_affiliation_strings":["Huawei Noah’s Ark Lab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070122547","display_name":"Renyu Wang","orcid":"https://orcid.org/0009-0009-7796-7133"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renyu Wang","raw_affiliation_strings":["Huawei Noah’s Ark Lab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab,China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2104,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80862449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6277","last_page":"6281"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9961000084877014,"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":0.7741733193397522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7673946619033813},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5692057013511658},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.5589141249656677},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5255982875823975},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4806308150291443},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4653658866882324},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4571634531021118},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4461362659931183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39530718326568604},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3595525622367859},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.0951271653175354},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09386438131332397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741733193397522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7673946619033813},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5692057013511658},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.5589141249656677},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5255982875823975},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4806308150291443},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4653658866882324},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4571634531021118},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4461362659931183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39530718326568604},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3595525622367859},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0951271653175354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09386438131332397},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746609","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1934041838","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2146324387","https://openalex.org/W2530876040","https://openalex.org/W2559260703","https://openalex.org/W2749337587","https://openalex.org/W2916979304","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2962946733","https://openalex.org/W2963045393","https://openalex.org/W2963103134","https://openalex.org/W2963321191","https://openalex.org/W2964058413","https://openalex.org/W2972592847","https://openalex.org/W3015312544","https://openalex.org/W3028077980","https://openalex.org/W3083872384","https://openalex.org/W3096090308","https://openalex.org/W3099330747","https://openalex.org/W3134695619","https://openalex.org/W3161525290","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2342810974","https://openalex.org/W2058482658","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W1823208675","https://openalex.org/W3135613579","https://openalex.org/W3209446892","https://openalex.org/W2345688450","https://openalex.org/W2037635165"],"abstract_inverted_index":{"Single-channel":[0],"speech":[1,5,14,44,61,80,98,140],"enhancement":[2,15,62,141],"for":[3,60,94,112],"automatic":[4],"recognition":[6],"(ASR)":[7],"has":[8],"been":[9],"widely":[10],"studied.":[11],"However,":[12],"most":[13],"methods":[16,123,142,148],"conduct":[17],"over":[18],"suppression":[19],"and":[20,63,72,82,97,143,152,190],"introduce":[21],"distortion,":[22],"which":[23,91],"limits":[24],"performance":[25],"gains":[26],"or":[27],"even":[28],"deteriorates":[29],"the":[30,41,47,121,133,153,174],"back-end":[31,170],"performance.":[32,118],"The":[33,129],"key":[34],"to":[35,114],"solving":[36],"this":[37],"problem":[38],"is":[39,110],"preserving":[40],"integrity":[42],"of":[43,68,156,188],"while":[45],"suppressing":[46],"background":[48],"noises.":[49],"There-fore,":[50],"we":[51,102],"propose":[52],"a":[53,159,167],"time":[54,138],"domain":[55,139,145],"progressive":[56,70,146],"learning":[57,147],"(TDPL)":[58],"approach":[59],"ASR.":[64],"TDPL":[65,113,134,157],"model":[66],"consists":[67],"encoder,":[69],"enhancer":[71],"decoder.":[73],"Both":[74],"SNR-increased":[75],"intermediate":[76,154],"target":[77,84],"with":[78,85,166],"less":[79],"distortion":[81],"clean":[83,176],"better":[86],"listening":[87],"quality/intelligibility":[88],"are":[89,92],"learned,":[90],"provided":[93],"ASR":[95,117,150,169],"pre-processing":[96],"communication,":[99],"respectively.":[100],"Additionally,":[101],"also":[103],"present":[104],"an":[105],"SNR":[106],"constriction":[107],"loss":[108],"that":[109,132],"fit":[111],"further":[115],"improve":[116],"We":[119],"evaluate":[120],"proposed":[122],"on":[124,181],"CHiME-4":[125,182],"real":[126],"evaluation":[127,184],"set.":[128],"results":[130],"show":[131],"method":[135],"significantly":[136],"outperforms":[137],"frequency":[144],"in":[149,186],"task,":[151],"output":[155,177],"achieves":[158,178],"36.3%":[160],"relative":[161],"word":[162],"error":[163],"rate":[164],"reduction":[165],"powerful":[168],"without":[171],"retraining.":[172],"Moreover,":[173],"estimated":[175],"certain":[179],"improvement":[180],"simulation":[183],"set":[185],"terms":[187],"PESQ":[189],"STOI":[191],"measures.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}