{"id":"https://openalex.org/W3207354624","doi":"https://doi.org/10.1109/icassp43922.2022.9746994","title":"Improving Emotional Speech Synthesis by Using SUS-Constrained VAE and Text Encoder Aggregation","display_name":"Improving Emotional Speech Synthesis by Using SUS-Constrained VAE and Text Encoder Aggregation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207354624","doi":"https://doi.org/10.1109/icassp43922.2022.9746994","mag":"3207354624"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746994","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5036283087","display_name":"Fengyu Yang","orcid":"https://orcid.org/0009-0005-5410-4707"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengyu Yang","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054843960","display_name":"Jian Luan","orcid":"https://orcid.org/0000-0002-2383-226X"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Luan","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362598","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0002-0921-0122"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7267,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69408958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8302","last_page":"8306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/encoder","display_name":"Encoder","score":0.7966492772102356},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.791128396987915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7784945964813232},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5953280329704285},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5797210931777954},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5381866693496704},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5302581191062927},{"id":"https://openalex.org/keywords/cohesion","display_name":"Cohesion (chemistry)","score":0.5174111127853394},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43306854367256165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39553314447402954},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.22468528151512146},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08291816711425781}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7966492772102356},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.791128396987915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7784945964813232},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5953280329704285},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5797210931777954},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5381866693496704},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5302581191062927},{"id":"https://openalex.org/C104054115","wikidata":"https://www.wikidata.org/wiki/Q216828","display_name":"Cohesion (chemistry)","level":2,"score":0.5174111127853394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43306854367256165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39553314447402954},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.22468528151512146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08291816711425781},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746994","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2187089797","https://openalex.org/W2770743791","https://openalex.org/W2793479148","https://openalex.org/W2794490148","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2946200149","https://openalex.org/W2962691331","https://openalex.org/W2963272440","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2966387353","https://openalex.org/W2970730223","https://openalex.org/W2972885185","https://openalex.org/W3010916717","https://openalex.org/W3015440759","https://openalex.org/W3015841875","https://openalex.org/W3015922793","https://openalex.org/W3095401840","https://openalex.org/W3125481789","https://openalex.org/W3133185996","https://openalex.org/W3162791003","https://openalex.org/W4298580827","https://openalex.org/W6640963894","https://openalex.org/W6746238782","https://openalex.org/W6748409065","https://openalex.org/W6750489868","https://openalex.org/W6763832098","https://openalex.org/W6773153034","https://openalex.org/W6789577077","https://openalex.org/W6791022691"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2129146436","https://openalex.org/W2032507829"],"abstract_inverted_index":{"Learning":[0],"emotion":[1,22,51,60],"embedding":[2,23,52,61],"from":[3,79],"reference":[4],"audio":[5],"is":[6,62],"a":[7],"straightforward":[8],"approach":[9],"for":[10],"multi-emotion":[11],"speech":[12],"synthesis":[13],"in":[14],"encoder-decoder":[15],"systems.":[16],"But":[17],"how":[18,25],"to":[19,26,47,66],"get":[20],"better":[21,54],"and":[24,98,101],"inject":[27],"it":[28],"into":[29],"TTS":[30],"acoustic":[31],"model":[32],"more":[33,103],"effectively":[34],"are":[35,83],"still":[36],"under":[37],"investigation.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"an":[44],"innovative":[45],"constraint":[46],"help":[48],"VAE":[49],"extract":[50],"with":[53],"cluster":[55],"cohesion.":[56],"Besides,":[57],"the":[58,77,88,93],"obtained":[59],"used":[63],"as":[64],"query":[65],"aggregate":[67],"latent":[68],"representations":[69],"of":[70,95],"all":[71],"encoder":[72,80],"layers":[73,81],"via":[74],"attention.":[75],"Moreover,":[76],"queries":[78],"themselves":[82],"also":[84],"helpful.":[85],"Experiments":[86],"prove":[87],"proposed":[89],"methods":[90],"can":[91],"enhance":[92],"encoding":[94],"comprehensive":[96],"syntactic":[97],"semantic":[99],"information":[100],"produce":[102],"expressive":[104],"emotional":[105],"speech.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}