{"id":"https://openalex.org/W4390451916","doi":"https://doi.org/10.1145/3611380.3628555","title":"PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognition","display_name":"PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390451916","doi":"https://doi.org/10.1145/3611380.3628555"},"language":"en","primary_location":{"id":"doi:10.1145/3611380.3628555","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611380.3628555","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628555","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia Workshops","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628555","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111103714","display_name":"Chengxi Lei","orcid":"https://orcid.org/0009-0003-5799-5977"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengxi Lei","raw_affiliation_strings":["School of Artificial Intelligence, Dalian Maritime University, China and School of Mathematical and Computational Sciences, Massey university, New Zealand"],"raw_orcid":"https://orcid.org/0009-0003-5799-5977","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Dalian Maritime University, China and School of Mathematical and Computational Sciences, Massey university, New Zealand","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070580244","display_name":"Satwinder Singh","orcid":"https://orcid.org/0000-0001-9032-6781"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Satwinder Singh","raw_affiliation_strings":["School of Mathematical and Computational Sciences, Massey University, New Zealand"],"raw_orcid":"https://orcid.org/0000-0001-9032-6781","affiliations":[{"raw_affiliation_string":"School of Mathematical and Computational Sciences, Massey University, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041651091","display_name":"Feng Hou","orcid":"https://orcid.org/0000-0001-5776-9177"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Feng Hou","raw_affiliation_strings":["School of Mathematical and Computational Sciences, Massey University, New Zealand"],"raw_orcid":"https://orcid.org/0000-0001-5776-9177","affiliations":[{"raw_affiliation_string":"School of Mathematical and Computational Sciences, Massey University, New Zealand","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042297936","display_name":"Xiaoyun Jia","orcid":"https://orcid.org/0000-0002-5525-9349"},"institutions":[{"id":"https://openalex.org/I1292020679","display_name":"Institute on Governance","ror":"https://ror.org/00ppf7x29","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I1292020679"]},{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Xiaoyun Jia","raw_affiliation_strings":["Institute of Governance &amp; School of Political Science and Public Administration, Shandong University, CN"],"raw_orcid":"https://orcid.org/0000-0002-5525-9349","affiliations":[{"raw_affiliation_string":"Institute of Governance &amp; School of Political Science and Public Administration, Shandong University, CN","institution_ids":["https://openalex.org/I1292020679","https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022594144","display_name":"Ruili Wang","orcid":"https://orcid.org/0000-0003-2899-9816"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]},{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["CN","NZ"],"is_corresponding":false,"raw_author_name":"Ruili Wang","raw_affiliation_strings":["School of Mathematical and Computational Sciences, Massey University, NZ and School of Artificial Intelligence, Dalian Maritime University, China"],"raw_orcid":"https://orcid.org/0000-0003-2899-9816","affiliations":[{"raw_affiliation_string":"School of Mathematical and Computational Sciences, Massey University, NZ and School of Artificial Intelligence, Dalian Maritime University, China","institution_ids":["https://openalex.org/I43313876","https://openalex.org/I51158804"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111103714"],"corresponding_institution_ids":["https://openalex.org/I43313876"],"apc_list":null,"apc_paid":null,"fwci":0.3408,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67952637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.7367736101150513},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7170354723930359},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6114341020584106},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.5521537065505981},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5250698924064636},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5156273245811462},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.4758586287498474},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.46177753806114197},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4430190920829773},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.1957521140575409},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08076074719429016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367736101150513},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7170354723930359},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6114341020584106},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.5521537065505981},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5250698924064636},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5156273245811462},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.4758586287498474},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.46177753806114197},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4430190920829773},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.1957521140575409},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08076074719429016},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3611380.3628555","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611380.3628555","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628555","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia Workshops","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3611380.3628555","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3611380.3628555","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3611380.3628555","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia Workshops","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321983","display_name":"Ministry of Business, Innovation and Employment","ror":"https://ror.org/02jtq1b51"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390451916.pdf","grobid_xml":"https://content.openalex.org/works/W4390451916.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1922655562","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2407080277","https://openalex.org/W2407277936","https://openalex.org/W2617258110","https://openalex.org/W2765407302","https://openalex.org/W2962824709","https://openalex.org/W2992308087","https://openalex.org/W2995181338","https://openalex.org/W3015585292","https://openalex.org/W3036601975","https://openalex.org/W3094833745","https://openalex.org/W3144810982","https://openalex.org/W3163839574","https://openalex.org/W3196782138","https://openalex.org/W4224933812","https://openalex.org/W4286899907","https://openalex.org/W4297841801","https://openalex.org/W4297853167","https://openalex.org/W4375868903","https://openalex.org/W4375869379","https://openalex.org/W4385774701","https://openalex.org/W6929382529"],"related_works":["https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2005708641","https://openalex.org/W2395719637","https://openalex.org/W1940093498","https://openalex.org/W2050397613","https://openalex.org/W2080458333","https://openalex.org/W2400533375","https://openalex.org/W2470236000","https://openalex.org/W2097143083"],"abstract_inverted_index":{"Most":[0],"of":[1,18,40,43,76,154],"the":[2,11,15,37,74,91,104,111,120,133,140,152,158],"current":[3,159],"speech":[4,27,77],"data":[5,28],"augmentation":[6,29,117,147,162],"methods":[7],"operate":[8],"on":[9,36,82],"either":[10],"raw":[12],"waveform":[13],"or":[14],"amplitude":[16,145,160],"spectrum":[17,39,57],"speech.":[19,41],"In":[20],"this":[21],"paper,":[22],"we":[23],"propose":[24],"a":[25,46,49,60,63,68],"novel":[26],"method":[30,122],"called":[31],"PhasePerturbation":[32,52,92,155],"that":[33],"operates":[34],"dynamically":[35],"phase":[38,47,56],"Instead":[42],"statically":[44],"rotating":[45],"by":[48,87,131],"constant":[50],"degree,":[51],"utilizes":[53],"three":[54],"dynamic":[55],"operations,":[58],"i.e.,":[59],"randomization":[61],"operation,":[62,66,71],"frequency":[64],"masking":[65,70],"and":[67,127,139],"temporal":[69],"to":[72,156],"enhance":[73],"diversity":[75],"data.":[78],"We":[79],"conduct":[80],"experiments":[81],"wav2vec2.0":[83],"pre-trained":[84],"ASR":[85],"models":[86],"fine-tuning":[88],"them":[89],"with":[90,110],"augmented":[93],"TIMIT":[94],"corpus.":[95],"The":[96,149],"experimental":[97],"results":[98,150],"demonstrate":[99],"10.9%":[100],"relative":[101],"reduction":[102],"in":[103,129],"word":[105],"error":[106],"rate":[107],"(WER)":[108],"compared":[109],"baseline":[112],"model":[113],"fine-tuned":[114],"without":[115],"any":[116],"operation.":[118],"Furthermore,":[119],"proposed":[121],"achieves":[123],"additional":[124],"improvements":[125],"(12.9%":[126],"15.9%)":[128],"WER":[130],"complementing":[132],"Vocal":[134],"Tract":[135],"Length":[136],"Perturbation":[137],"(VTLP)":[138],"SpecAug,":[141],"which":[142],"are":[143],"both":[144],"spectrum-based":[146,161],"methods.":[148,163],"highlight":[151],"capability":[153],"improve":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
