{"id":"https://openalex.org/W4392902611","doi":"https://doi.org/10.1109/icassp48485.2024.10447774","title":"Low-Latency Speech Enhancement via Speech Token Generation","display_name":"Low-Latency Speech Enhancement via Speech Token Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902611","doi":"https://doi.org/10.1109/icassp48485.2024.10447774"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5031445620","display_name":"Huaying Xue","orcid":"https://orcid.org/0009-0002-7110-5574"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huaying Xue","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024977056","display_name":"Xiulian Peng","orcid":"https://orcid.org/0000-0001-8213-4878"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiulian Peng","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024989555","display_name":"Yan L\u00fc","orcid":"https://orcid.org/0000-0003-0900-7164"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Lu","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031445620"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":2.0731,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8672815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"661","last_page":"665"},"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/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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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":0.8017883896827698},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7496564388275146},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6959619522094727},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6122449040412903},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5705739259719849},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5162891745567322},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5059165358543396},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4827527403831482},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.46923738718032837},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4630216956138611},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4455816149711609},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.44395869970321655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3595670461654663},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21280837059020996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8017883896827698},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7496564388275146},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6959619522094727},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6122449040412903},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5705739259719849},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5162891745567322},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5059165358543396},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4827527403831482},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.46923738718032837},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4630216956138611},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4455816149711609},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.44395869970321655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3595670461654663},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21280837059020996},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":23,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1897240248","https://openalex.org/W2069681747","https://openalex.org/W2291877678","https://openalex.org/W2404892923","https://openalex.org/W2940275453","https://openalex.org/W2952218014","https://openalex.org/W2996969697","https://openalex.org/W2998161426","https://openalex.org/W3015199127","https://openalex.org/W3096159803","https://openalex.org/W3099330747","https://openalex.org/W3163296124","https://openalex.org/W4200483526","https://openalex.org/W4221167707","https://openalex.org/W4225287045","https://openalex.org/W4225302959","https://openalex.org/W4225905067","https://openalex.org/W4313679638","https://openalex.org/W4372266927","https://openalex.org/W4377231659","https://openalex.org/W4381786045","https://openalex.org/W6848735303"],"related_works":["https://openalex.org/W137020845","https://openalex.org/W1542588102","https://openalex.org/W3211091508","https://openalex.org/W2496295964","https://openalex.org/W2151333624","https://openalex.org/W1976952689","https://openalex.org/W2910493550","https://openalex.org/W1984921740","https://openalex.org/W4319347033","https://openalex.org/W1572861854"],"abstract_inverted_index":{"Existing":[0],"deep":[1],"learning":[2],"based":[3,162],"speech":[4,59,63,75,90,95,102,107,131,153,159,171,198],"enhancement":[5,60],"mainly":[6],"employ":[7],"a":[8,18,62,85,100,157],"data-driven":[9,189],"approach,":[10],"which":[11,92],"leverage":[12,148,156],"large":[13],"amounts":[14],"of":[15,20,77,99,193],"data":[16,36],"with":[17,128,173],"variety":[19],"noise":[21,25,194],"types":[22],"to":[23,124,133,139,151,168],"achieve":[24,169],"removal":[26],"from":[27,144],"noisy":[28,69,112,126],"signal.":[29],"However,":[30],"the":[31,35,41,54,68,106,129,135,164],"high":[32,170],"dependence":[33],"on":[34,40,53,67,110,163,178],"limits":[37],"its":[38,186],"generalization":[39],"unseen":[42],"complex":[43],"noises":[44],"in":[45,114,191],"real-life":[46],"environment.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,72,83,119,155],"focus":[52],"low-latency":[55],"scenario":[56],"and":[57,79,104,137,181,196],"regard":[58],"as":[61],"generation":[64,160],"problem":[65],"conditioned":[66,109],"signal,":[70],"where":[71],"generate":[73,152],"clean":[74,94],"instead":[76],"identifying":[78],"removing":[80],"noises.":[81],"Specifically,":[82],"propose":[84,120],"conditional":[86],"generative":[87],"framework":[88],"for":[89],"enhancement,":[91],"models":[93],"by":[96],"acoustic":[97],"codes":[98,108],"neural":[101,166],"codec":[103,167],"generates":[105],"past":[111],"frames":[113,127],"an":[115,121],"auto-regressive":[116],"way.":[117],"Moreover,":[118],"explicitalignment":[122],"approach":[123,161],"align":[125],"generated":[130],"tokens":[132],"improve":[134],"robustness":[136,195],"scalability":[138],"different":[140],"input":[141],"lengths.":[142],"Different":[143],"other":[145],"methods":[146],"that":[147],"multiple":[149],"stages":[150],"codes,":[154],"single-stage":[158],"TF-Codec":[165],"quality":[172],"low":[174],"latency.":[175],"Extensive":[176],"results":[177],"both":[179],"synthetic":[180],"real-recorded":[182],"test":[183],"set":[184],"show":[185],"superiority":[187],"over":[188],"approaches":[190],"terms":[192],"temporal":[197],"coherence.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}