{"id":"https://openalex.org/W4392903247","doi":"https://doi.org/10.1109/icassp48485.2024.10447759","title":"AutoPrep: An Automatic Preprocessing Framework for In-The-Wild Speech Data","display_name":"AutoPrep: An Automatic Preprocessing Framework for In-The-Wild Speech Data","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903247","doi":"https://doi.org/10.1109/icassp48485.2024.10447759"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447759","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/A5004643540","display_name":"Jianwei Yu","orcid":"https://orcid.org/0000-0002-2449-1436"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianwei Yu","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048946763","display_name":"Hangting Chen","orcid":"https://orcid.org/0000-0002-4085-4364"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangting Chen","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017831085","display_name":"Yanyao Bian","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyao Bian","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100706630","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-0018-3711"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614741","display_name":"Yi Luo","orcid":"https://orcid.org/0009-0004-2304-3684"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068192693","display_name":"Jinchuan Tian","orcid":"https://orcid.org/0000-0002-2129-471X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinchuan Tian","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462413","display_name":"Mengyang Liu","orcid":"https://orcid.org/0000-0002-8862-5966"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyang Liu","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101437175","display_name":"Jiayi Jiang","orcid":"https://orcid.org/0000-0003-0673-848X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Jiang","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055716987","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-1796-7280"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data","institution_ids":["https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5004643540"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":2.5459,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90163749,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1136","last_page":"1140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9955000281333923,"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":0.9950000047683716,"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":0.8219085931777954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7171862125396729},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6661955118179321},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6233090162277222},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5863033533096313},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5343382358551025},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5003945827484131},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49516716599464417},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.49291157722473145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4855642020702362},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48399946093559265},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.45507872104644775},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4494761824607849},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4134431481361389},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.39371028542518616},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07345989346504211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219085931777954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7171862125396729},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6661955118179321},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6233090162277222},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5863033533096313},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5343382358551025},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5003945827484131},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49516716599464417},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.49291157722473145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4855642020702362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48399946093559265},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.45507872104644775},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4494761824607849},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4134431481361389},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.39371028542518616},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07345989346504211},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447759","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":[{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2144499799","https://openalex.org/W2402146185","https://openalex.org/W2603567530","https://openalex.org/W2971753973","https://openalex.org/W2972359262","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3159481202","https://openalex.org/W3171302872","https://openalex.org/W3174758275","https://openalex.org/W3198533616","https://openalex.org/W3203407300","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4206908380","https://openalex.org/W4225302959","https://openalex.org/W4285182445","https://openalex.org/W4313679638","https://openalex.org/W4323066695","https://openalex.org/W4372260557","https://openalex.org/W4372262790","https://openalex.org/W4372340947","https://openalex.org/W4379924545","https://openalex.org/W4381786045","https://openalex.org/W4385822305","https://openalex.org/W4385823191","https://openalex.org/W4388017359","https://openalex.org/W4390075359","https://openalex.org/W6767453231","https://openalex.org/W6780218876","https://openalex.org/W6796730497","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6850218400","https://openalex.org/W6852870047"],"related_works":["https://openalex.org/W2550171623","https://openalex.org/W596245619","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W4388404911","https://openalex.org/W1987021544","https://openalex.org/W2009814707"],"abstract_inverted_index":{"Recently,":[0],"the":[1,11,20,28,45,75,144,154],"utilization":[2],"of":[3,13,22,44,58,80],"extensive":[4],"open-sourced":[5,145,171],"text":[6],"data":[7,26,49,82,98,161],"has":[8],"significantly":[9],"advanced":[10],"performance":[12],"text-based":[14],"large":[15],"language":[16],"models":[17],"(LLMs).":[18],"However,":[19],"use":[21],"in-the-wild":[23,96],"large-scale":[24],"speech":[25,29,48,55,59,81,97,110,126,128,133,139],"in":[27,102],"technology":[30],"community":[31],"remains":[32],"constrained.":[33],"One":[34],"reason":[35],"for":[36],"this":[37,90,103],"limitation":[38],"is":[39,50,83,106],"that":[40,153],"a":[41],"considerable":[42],"amount":[43],"publicly":[46],"available":[47],"compromised":[51],"by":[52],"background":[53],"noise,":[54],"overlapping,":[56],"lack":[57],"segmentation":[60],"information,":[61],"missing":[62],"speaker":[63,113,130,184],"labels,":[64,114],"and":[65,86,115,137,147,165],"incomplete":[66],"transcriptions,":[67],"which":[68,105],"can":[69,158,178],"largely":[70],"hinder":[71],"their":[72],"usefulness.":[73],"On":[74],"other":[76],"hand,":[77],"human":[78],"annotation":[79],"both":[84],"time-consuming":[85],"costly.":[87],"To":[88],"address":[89],"issue,":[91],"we":[92],"introduce":[93],"an":[94],"automatic":[95,138],"preprocessing":[99],"framework":[100,122,157],"(AutoPrep)":[101],"paper,":[104],"designed":[107],"to":[108,169,181],"enhance":[109],"quality,":[111],"generate":[112,159],"produce":[116],"transcriptions":[117],"automatically.":[118],"The":[119,174],"proposed":[120,155],"AutoPrep":[121,156],"comprises":[123],"six":[124],"components:":[125],"enhancement,":[127],"segmentation,":[129],"clustering,":[131],"target":[132],"extraction,":[134],"quality":[135],"filtering":[136],"recognition.":[140],"Experiments":[141],"conducted":[142],"on":[143],"WenetSpeech":[146],"our":[148],"self-collected":[149],"AutoPrepWild":[150],"corpora":[151],"demonstrate":[152],"preprocessed":[160],"with":[162],"similar":[163],"DNSMOS":[164],"PDNSMOS":[166],"scores":[167],"compared":[168],"several":[170],"TTS":[172,176],"datasets.":[173],"corresponding":[175],"system":[177],"achieve":[179],"up":[180],"0.68":[182],"in-domain":[183],"similarity.":[185],"<sup":[186],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[187],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}