{"id":"https://openalex.org/W2797972631","doi":"https://doi.org/10.1109/icassp.2018.8461944","title":"A Hybrid Approach to Combining Conventional and Deep Learning Techniques for Single-Channel Speech Enhancement and Recognition","display_name":"A Hybrid Approach to Combining Conventional and Deep Learning Techniques for Single-Channel Speech Enhancement and Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2797972631","doi":"https://doi.org/10.1109/icassp.2018.8461944","mag":"2797972631"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/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, Anhui, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Tashev","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084618329","display_name":"Shuayb Zarar","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuayb Zarar","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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"],"raw_orcid":null,"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":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3254,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.932347,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"2531","last_page":"2535"},"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":0.9975000023841858,"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":0.8291888236999512},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.8103625774383545},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7573580741882324},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7423978447914124},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.639609694480896},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5535163879394531},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.548607587814331},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5203104019165039},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5006880760192871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4731139838695526},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4467044770717621},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4403942823410034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291888236999512},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8103625774383545},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7573580741882324},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7423978447914124},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.639609694480896},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5535163879394531},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.548607587814331},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5203104019165039},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5006880760192871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4731139838695526},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4467044770717621},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4403942823410034},{"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/icassp.2018.8461944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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","display_name":"Peace, Justice and strong institutions","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W190004713","https://openalex.org/W217932999","https://openalex.org/W258661521","https://openalex.org/W1510355813","https://openalex.org/W1975301756","https://openalex.org/W2032252376","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2094461119","https://openalex.org/W2119796132","https://openalex.org/W2121973264","https://openalex.org/W2127851351","https://openalex.org/W2128653836","https://openalex.org/W2168379380","https://openalex.org/W2181607856","https://openalex.org/W2394932179","https://openalex.org/W2486913545","https://openalex.org/W2507424718","https://openalex.org/W2613495131","https://openalex.org/W2997829126","https://openalex.org/W3147539069","https://openalex.org/W6609686331","https://openalex.org/W6662385463","https://openalex.org/W6677886673"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W4386746628","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W2166831097","https://openalex.org/W4312751558"],"abstract_inverted_index":{"Conventional":[0],"speech-enhancement":[1,86,117],"techniques":[2],"employ":[3],"statistical":[4],"signal-processing":[5],"algorithms.":[6],"They":[7],"are":[8,24,107],"computationally":[9],"efficient":[10],"and":[11,100,110,174,192],"improve":[12],"speech":[13],"quality":[14],"even":[15],"under":[16,102],"unknown":[17,109],"noise":[18,69,105],"conditions.":[19],"For":[20],"these":[21,34,63],"reasons,":[22],"they":[23,38],"preferred":[25],"for":[26],"deployment":[27],"in":[28,75],"unpredictable":[29],"environments.":[30],"One":[31],"limitation":[32,58],"of":[33,59,92,104,124,171,190,198],"algorithms":[35,50,64],"is":[36],"that":[37,71,88,106],"fail":[39],"to":[40,55,95,119,163],"suppress":[41],"non-stationary":[42],"noise.":[43],"This":[44],"hinders":[45],"their":[46],"broad":[47],"usage.":[48],"Emerging":[49],"based":[51,151],"on":[52,152,179],"deep-learning":[53],"promise":[54],"overcome":[56],"this":[57,80,144,161,180],"conventional":[60,116],"methods.":[61],"However,":[62],"under-perform":[65],"when":[66],"presented":[67],"with":[68,134],"conditions":[70,103],"were":[72],"not":[73],"captured":[74],"the":[76,90,97,125,139],"training":[77,183],"data.":[78],"In":[79],"paper,":[81],"we":[82,159,186],"propose":[83],"a":[84,115,148,168,175,193],"single-channel":[85],"technique":[87],"combines":[89],"benefits":[91],"both":[93,108],"worlds":[94],"achieve":[96],"best":[98],"listening-quality":[99],"recognition-accuracy":[101],"nonstationary.":[111],"Our":[112],"method":[113],"utilizes":[114],"algorithm":[118],"produce":[120],"an":[121],"intermediate":[122,145],"representation":[123,146],"input":[126,131],"data":[127],"by":[128],"multiplying":[129],"noisy":[130],"spectrogram":[132],"features":[133,173],"gain":[135],"vectors":[136],"(known":[137],"as":[138],"suppression":[140],"rule).":[141],"We":[142],"process":[143],"through":[147],"recurrent":[149],"neural-network":[150],"long":[153],"short-term":[154],"memory":[155],"(LSTM)":[156],"units.":[157],"Furthermore,":[158],"train":[160],"network":[162],"jointly":[164],"learn":[165],"two":[166],"targets:":[167],"direct":[169],"estimate":[170],"clean-speech":[172],"noise-reduction":[176],"mask.":[177],"Based":[178],"LSTM":[181],"multi-style":[182],"(LSTM-MT)":[184],"architecture,":[185],"demonstrate":[187],"PESQ":[188],"improvement":[189],"0.76":[191],"relative":[194],"word-error":[195],"rate":[196],"reduction":[197],"47.73%.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}