{"id":"https://openalex.org/W4375868903","doi":"https://doi.org/10.1109/icassp49357.2023.10096374","title":"PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping","display_name":"PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868903","doi":"https://doi.org/10.1109/icassp49357.2023.10096374"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5072915273","display_name":"Junhyeok Lee","orcid":"https://orcid.org/0000-0002-4950-5371"},"institutions":[{"id":"https://openalex.org/I2799419483","display_name":"Applied Minds (United States)","ror":"https://ror.org/03szmqd24","country_code":"US","type":"company","lineage":["https://openalex.org/I2799419483"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junhyeok Lee","raw_affiliation_strings":["MINDsLab Inc.,Republic of Korea","MINDsLab Inc., Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MINDsLab Inc.,Republic of Korea","institution_ids":["https://openalex.org/I2799419483"]},{"raw_affiliation_string":"MINDsLab Inc., Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035383890","display_name":"Seungu Han","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungu Han","raw_affiliation_strings":["Seoul National University (SNU),Republic of Korea","Seoul National University (SNU), Republic of Korea","Supertone Inc., Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University (SNU),Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University (SNU), Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Supertone Inc., Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064518610","display_name":"Hyunjae Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I2799419483","display_name":"Applied Minds (United States)","ror":"https://ror.org/03szmqd24","country_code":"US","type":"company","lineage":["https://openalex.org/I2799419483"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Hyunjae Cho","raw_affiliation_strings":["MINDsLab Inc.,Republic of Korea","MINDsLab Inc., Republic of Korea","Seoul National University (SNU), Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MINDsLab Inc.,Republic of Korea","institution_ids":["https://openalex.org/I2799419483"]},{"raw_affiliation_string":"MINDsLab Inc., Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Seoul National University (SNU), Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083897431","display_name":"Wonbin Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I2799419483","display_name":"Applied Minds (United States)","ror":"https://ror.org/03szmqd24","country_code":"US","type":"company","lineage":["https://openalex.org/I2799419483"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Wonbin Jung","raw_affiliation_strings":["MINDsLab Inc.,Republic of Korea","MINDsLab Inc., Republic of Korea","Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MINDsLab Inc.,Republic of Korea","institution_ids":["https://openalex.org/I2799419483"]},{"raw_affiliation_string":"MINDsLab Inc., Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9994000196456909,"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":0.7649164795875549},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.745018482208252},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7402553558349609},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.585795521736145},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5371179580688477},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5293874144554138},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5155239105224609},{"id":"https://openalex.org/keywords/bin","display_name":"Bin","score":0.5123818516731262},{"id":"https://openalex.org/keywords/signal-generator","display_name":"Signal generator","score":0.5084987878799438},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5043712854385376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45636481046676636},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4558003544807434},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44815126061439514},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4220528304576874},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40597692131996155},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33016064763069153},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.32487115263938904},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2939401865005493},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.16339874267578125},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10674935579299927},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08823421597480774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649164795875549},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.745018482208252},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7402553558349609},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.585795521736145},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5371179580688477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5293874144554138},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5155239105224609},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.5123818516731262},{"id":"https://openalex.org/C207912722","wikidata":"https://www.wikidata.org/wiki/Q1259123","display_name":"Signal generator","level":3,"score":0.5084987878799438},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5043712854385376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45636481046676636},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4558003544807434},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44815126061439514},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4220528304576874},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40597692131996155},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33016064763069153},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.32487115263938904},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2939401865005493},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.16339874267578125},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10674935579299927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08823421597480774},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/10","score":0.699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2107860279","https://openalex.org/W2962866891","https://openalex.org/W2970006822","https://openalex.org/W3015338123","https://openalex.org/W3034720584","https://openalex.org/W3092028330","https://openalex.org/W3097828251","https://openalex.org/W3099088591","https://openalex.org/W3161890269","https://openalex.org/W3169905056","https://openalex.org/W3174807077","https://openalex.org/W3196468212","https://openalex.org/W3197334236","https://openalex.org/W4225276642","https://openalex.org/W4281736089","https://openalex.org/W4283215837","https://openalex.org/W4286899907","https://openalex.org/W4301371414","https://openalex.org/W4320013936","https://openalex.org/W4382202681","https://openalex.org/W6767111847","https://openalex.org/W6779093361","https://openalex.org/W6780507278","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6797179183","https://openalex.org/W6802838302","https://openalex.org/W6803547063","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4360764600","https://openalex.org/W2074460168","https://openalex.org/W2053531689","https://openalex.org/W2109142991","https://openalex.org/W1842536210","https://openalex.org/W2172523511","https://openalex.org/W2362052300","https://openalex.org/W1781713806","https://openalex.org/W2350061705"],"abstract_inverted_index":{"Previous":[0],"generative":[1],"adversarial":[2],"network":[3],"(GAN)-based":[4],"neural":[5],"vocoders":[6],"are":[7],"trained":[8],"to":[9,43,73],"reconstruct":[10],"the":[11,17,24,37,40,44,48,58,67],"exact":[12],"ground":[13],"truth":[14],"wave-form":[15],"from":[16],"paired":[18],"mel-spectrogram":[19],"and":[20,39,89],"do":[21],"not":[22],"consider":[23],"one-to-many":[25,75],"relationship":[26],"of":[27,69],"speech":[28,63],"synthesis.":[29],"This":[30],"conventional":[31],"training":[32],"causes":[33],"overfitting":[34],"for":[35,62],"both":[36],"discriminators":[38],"generator,":[41],"leading":[42],"periodicity":[45],"artifacts":[46],"in":[47],"generated":[49],"audio":[50,90],"signal.":[51],"In":[52],"this":[53],"work,":[54],"we":[55,81],"present":[56],"PhaseAug,":[57],"first":[59],"differentiable":[60],"augmentation":[61],"synthesis":[64],"that":[65],"rotates":[66],"phase":[68],"each":[70],"frequency":[71],"bin":[72],"simulate":[74],"mapping.":[76],"With":[77],"our":[78],"proposed":[79],"method,":[80],"outperform":[82],"baselines":[83],"without":[84],"any":[85],"architecture":[86],"modification.":[87],"Code":[88],"samples":[91],"will":[92],"be":[93],"available":[94],"at":[95],"https://github.com/mindslab-ai/phaseaug.":[96]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2023-05-10T00:00:00"}