{"id":"https://openalex.org/W3161525290","doi":"https://doi.org/10.1109/icassp39728.2021.9413395","title":"A Progressive Learning Approach to Adaptive Noise and Speech Estimation for Speech Enhancement and Noisy Speech Recognition","display_name":"A Progressive Learning Approach to Adaptive Noise and Speech Estimation for Speech Enhancement and Noisy Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161525290","doi":"https://doi.org/10.1109/icassp39728.2021.9413395","mag":"3161525290"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":true,"raw_author_name":"Zhaoxu Nian","raw_affiliation_strings":["University of Science and technology of China, Hefei, P. R. China"],"affiliations":[{"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/A5049067709","display_name":"Yan-Hui Tu","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":"Yan-Hui Tu","raw_affiliation_strings":["University of Science and technology of China, Hefei, P. R. China"],"affiliations":[{"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"],"affiliations":[{"raw_affiliation_string":"University of Science and technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005376611"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.2854,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.88857336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6913","last_page":"6917"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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/speech-recognition","display_name":"Speech recognition","score":0.8079907298088074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7774911522865295},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7080822587013245},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5442280173301697},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5336177349090576},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5286664962768555},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.51905757188797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44369906187057495},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42830580472946167},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.41165611147880554},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33522969484329224}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8079907298088074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774911522865295},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7080822587013245},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5442280173301697},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5336177349090576},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5286664962768555},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.51905757188797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44369906187057495},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42830580472946167},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.41165611147880554},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33522969484329224},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1825697635","https://openalex.org/W1934041838","https://openalex.org/W1967590528","https://openalex.org/W1969685872","https://openalex.org/W1975301756","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2057826000","https://openalex.org/W2069681747","https://openalex.org/W2094461119","https://openalex.org/W2146324387","https://openalex.org/W2153384885","https://openalex.org/W2171850596","https://openalex.org/W2530876040","https://openalex.org/W2559260703","https://openalex.org/W2749337587","https://openalex.org/W2797972631","https://openalex.org/W2807818604","https://openalex.org/W2891433113","https://openalex.org/W2962892438","https://openalex.org/W2962946733","https://openalex.org/W2963321191","https://openalex.org/W2972592847","https://openalex.org/W3010889951","https://openalex.org/W3028077980","https://openalex.org/W6730321509"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2401089611","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W4225315139","https://openalex.org/W2131486661","https://openalex.org/W2089240210","https://openalex.org/W2161396743","https://openalex.org/W4385881881"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,24,50,86,111,128],"progressive":[6,40,64],"learning-based":[7],"adaptive":[8],"noise":[9,26],"and":[10,36,47],"speech":[11,16,20,46,88,96,101,112,145],"estimation":[12],"(PL-ANSE)":[13],"method":[14],"for":[15,95],"preprocessing":[17],"in":[18],"noisy":[19,144],"recognition,":[21],"leveraging":[22],"upon":[23],"frame-level":[25],"tracking":[27],"capability":[28],"of":[29,42,135],"improved":[30],"minima":[31],"controlled":[32],"recursive":[33],"averaging":[34],"(IMCRA)":[35],"an":[37],"utterance-level":[38],"deep":[39],"learning":[41],"nonlinear":[43],"interactions":[44],"between":[45],"noise.":[48],"First,":[49],"bi-directional":[51],"long":[52],"short-term":[53],"memory":[54],"model":[55],"is":[56,107],"adopted":[57],"at":[58,79,91],"each":[59],"network":[60],"layer":[61],"to":[62,115,139,148],"learn":[63],"ratio":[65],"masks":[66],"(PRMs)":[67],"as":[68],"targets":[69],"with":[70,142],"progressively":[71],"increasing":[72],"signal-to-noise":[73],"ratios.":[74],"Then,":[75],"the":[76,80,92,99,117,151],"estimated":[77],"PRMs":[78],"utterance":[81],"level":[82,94],"are":[83],"combined":[84],"within":[85],"conventional":[87],"enhancement":[89],"algorithm":[90],"frame":[93],"enhancement.":[97],"Finally,":[98],"enhanced":[100],"based":[102],"on":[103,150],"multi-level":[104],"information":[105],"fusion":[106],"directly":[108],"fed":[109],"into":[110],"recognition":[113,118],"system":[114],"improve":[116],"performance.":[119],"Experiments":[120],"show":[121],"that":[122],"our":[123],"proposed":[124],"approach":[125],"can":[126],"achieve":[127],"relative":[129],"word":[130],"error":[131],"rate":[132],"(WER)":[133],"reduction":[134],"22.1%":[136],"when":[137],"compared":[138],"results":[140],"attained":[141],"unprocessed":[143],"(from":[146],"23.84%":[147],"18.57%)":[149],"CHiME-4":[152],"single-channel":[153],"real":[154],"test":[155],"data.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}