{"id":"https://openalex.org/W4408355073","doi":"https://doi.org/10.1109/icassp49660.2025.10889460","title":"Self-supervised Prosody Learning at Phoneme-level with Momentum Contrast for Speech Synthesis","display_name":"Self-supervised Prosody Learning at Phoneme-level with Momentum Contrast for Speech Synthesis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355073","doi":"https://doi.org/10.1109/icassp49660.2025.10889460"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5000176539","display_name":"Zhao-Ci Liu","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":"Zhao-Ci Liu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059516164","display_name":"Ya-Jun Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya-Jun Hu","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK Co. Ltd.,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK Co. Ltd.,China","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430201","display_name":"Liping Chen","orcid":"https://orcid.org/0009-0003-6453-5645"},"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":"Liping Chen","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069176378","display_name":"Zhen-Hua Ling","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":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9848999977111816,"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":0.9848999977111816,"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/T12031","display_name":"Speech and dialogue systems","score":0.9391000270843506,"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":0.9218999743461609,"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/prosody","display_name":"Prosody","score":0.8632773160934448},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.7599756121635437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6490537524223328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6189862489700317},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5284989476203918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4380094110965729},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.366476833820343}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8632773160934448},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.7599756121635437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6490537524223328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6189862489700317},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5284989476203918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4380094110965729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.366476833820343}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2006689085","https://openalex.org/W2110358797","https://openalex.org/W2157225271","https://openalex.org/W2885800352","https://openalex.org/W2964243274","https://openalex.org/W3035524453","https://openalex.org/W3097003111","https://openalex.org/W3097892637","https://openalex.org/W3150572638","https://openalex.org/W3170320568","https://openalex.org/W3202510435","https://openalex.org/W3209059054","https://openalex.org/W4221159457","https://openalex.org/W4385572372","https://openalex.org/W4385822381","https://openalex.org/W4390926497","https://openalex.org/W4392903361","https://openalex.org/W4395957972","https://openalex.org/W4401806189","https://openalex.org/W6750489868","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6810007534","https://openalex.org/W6852870047","https://openalex.org/W6862144568"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"This":[0,30],"paper":[1],"investigates":[2],"leveraging":[3],"large-scale":[4],"speech":[5,12,37,72,100,109],"data":[6],"to":[7,45,58,67,80],"enhance":[8],"prosodic":[9],"modeling":[10],"in":[11,85],"synthesis,":[13],"and":[14,38,52,74],"introduces":[15],"a":[16,55,95],"model":[17,31,57,98],"named":[18],"SP2MC":[19,90],"which":[20,49],"achieves":[21],"self-supervised":[22],"prosody":[23,60],"learning":[24],"at":[25],"phoneme-level":[26,47,69],"with":[27],"momentum":[28],"contrast.":[29],"incorporates":[32],"dual":[33],"convolutional":[34],"encoders":[35],"for":[36,99],"linear":[39],"predictive":[40],"coding":[41],"(LPC)":[42],"residual":[43],"inputs":[44],"generate":[46,68],"embeddings,":[48],"are":[50,65,92],"masked":[51],"processed":[53],"by":[54,111],"Transformer":[56],"produce":[59],"representations.":[61],"Two":[62],"supervision":[63,70],"modules":[64],"employed":[66],"from":[71],"waveforms":[73],"residuals.":[75],"Momentum":[76],"contrast":[77],"is":[78,115],"utilized":[79],"manage":[81],"negative":[82],"sample":[83],"selection":[84],"contrastive":[86],"learning.":[87],"Finally,":[88],"the":[89,106,112],"representations":[91],"integrated":[93],"into":[94],"Fastspeech2-based":[96],"acoustic":[97],"synthesis.":[101],"Experimental":[102],"results":[103],"indicate":[104],"that":[105,119],"naturalness":[107],"of":[108,120],"synthesized":[110],"proposed":[113],"method":[114],"significantly":[116],"better":[117],"than":[118],"baselines.":[121]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}