{"id":"https://openalex.org/W4408352028","doi":"https://doi.org/10.1109/icassp49660.2025.10887968","title":"Anchored Monotonic Alignment and Representation Substitution for Rare Spontaneous Behaviors in Spontaneous Speech Synthesis","display_name":"Anchored Monotonic Alignment and Representation Substitution for Rare Spontaneous Behaviors in Spontaneous Speech Synthesis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352028","doi":"https://doi.org/10.1109/icassp49660.2025.10887968"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887968","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/A5082235402","display_name":"Ning-Qian Wu","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":"Ning-Qian Wu","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/A5102016471","display_name":"Yajun Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ya-Jun Hu","raw_affiliation_strings":["iFLYTEK Co. Ltd.,iFLYTEK Research,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Co. Ltd.,iFLYTEK Research,China","institution_ids":[]}]},{"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":1,"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/T12031","display_name":"Speech and dialogue systems","score":0.975600004196167,"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/T12031","display_name":"Speech and dialogue systems","score":0.975600004196167,"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/T12090","display_name":"Language and cultural evolution","score":0.9639000296592712,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9282000064849854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/substitution","display_name":"Substitution (logic)","score":0.7588461637496948},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.6459720134735107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6281911134719849},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5593010783195496},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4187623858451843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3890373110771179},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.320518434047699},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22203129529953003},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1454417109489441}],"concepts":[{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.7588461637496948},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.6459720134735107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6281911134719849},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5593010783195496},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4187623858451843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3890373110771179},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.320518434047699},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22203129529953003},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1454417109489441},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887968","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.550000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W183448665","https://openalex.org/W2310338327","https://openalex.org/W2537466733","https://openalex.org/W2791318011","https://openalex.org/W2972606665","https://openalex.org/W3016151952","https://openalex.org/W3021636956","https://openalex.org/W3193700177","https://openalex.org/W3194208059","https://openalex.org/W3198152857","https://openalex.org/W4312097353","https://openalex.org/W4385488985","https://openalex.org/W4385823163","https://openalex.org/W4385823196","https://openalex.org/W4392904093","https://openalex.org/W4399837985","https://openalex.org/W4402112175","https://openalex.org/W6778166081","https://openalex.org/W6796581206","https://openalex.org/W6810272389"],"related_works":["https://openalex.org/W2379444625","https://openalex.org/W2393147081","https://openalex.org/W2575869988","https://openalex.org/W4308647020","https://openalex.org/W2077314575","https://openalex.org/W2370088286","https://openalex.org/W2385568494","https://openalex.org/W4315701745","https://openalex.org/W1990290471","https://openalex.org/W4380682190"],"abstract_inverted_index":{"Spontaneous":[0],"behaviors":[1,62,125],"in":[2,38],"speech":[3,8,72],"pose":[4],"significant":[5],"challenges":[6],"for":[7],"synthesis.":[9],"Existing":[10],"research":[11],"has":[12],"not":[13],"adequately":[14],"addressed":[15],"these":[16,83,101],"behaviors,":[17],"with":[18],"most":[19],"studies":[20],"relying":[21],"on":[22],"specially":[23],"recorded":[24],"datasets.":[25],"In":[26,66],"contrast,":[27],"real-world":[28,75],"data":[29,51,76],"more":[30],"accurately":[31],"reflects":[32],"the":[33,58,78,108,111,119,132],"natural,":[34],"spontaneous":[35,47,61,71,93,124],"speaking":[36],"styles":[37],"everyday":[39],"life":[40],"and":[41,57,92,106,126],"encompasses":[42],"a":[43],"wider":[44],"range":[45],"of":[46,54,60,110,121],"behaviors.":[48],"However,":[49],"such":[50],"is":[52,63],"often":[53],"lower":[55],"quality,":[56],"distribution":[59],"highly":[64],"imbalanced.":[65],"this":[67],"study,":[68],"we":[69,85],"explore":[70],"synthesis":[73],"using":[74],"within":[77],"VITS2":[79],"framework.":[80],"To":[81],"overcome":[82],"challenges,":[84],"introduce":[86],"two":[87],"techniques:":[88],"anchored":[89],"monotonic":[90],"alignment":[91,105],"hidden":[94],"representation":[95],"substitution.":[96],"Experimental":[97],"results":[98],"demonstrate":[99],"that":[100],"methods":[102],"enhance":[103],"model":[104],"improve":[107],"naturalness":[109],"generated":[112],"speech.":[113,134],"Our":[114],"proposed":[115],"approach":[116],"successfully":[117],"addresses":[118],"challenge":[120],"synthesizing":[122],"rare":[123],"offers":[127],"users":[128],"flexible":[129],"control":[130],"over":[131],"synthesized":[133]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}