{"id":"https://openalex.org/W4406461588","doi":"https://doi.org/10.1109/slt61566.2024.10832354","title":"Fast, High-Quality and Parameter-Efficient Articulatory Synthesis Using Differentiable DSP","display_name":"Fast, High-Quality and Parameter-Efficient Articulatory Synthesis Using Differentiable DSP","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461588","doi":"https://doi.org/10.1109/slt61566.2024.10832354"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5101768356","display_name":"Yisi Liu","orcid":"https://orcid.org/0000-0002-0038-5399"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yisi Liu","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065383399","display_name":"Bohan Yu","orcid":"https://orcid.org/0009-0002-7568-936X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bohan Yu","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109796053","display_name":"Drake Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Drake Lin","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081837203","display_name":"Peter Wu","orcid":"https://orcid.org/0000-0001-6503-3936"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Wu","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015390421","display_name":"Cheol Jun Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheol Jun Cho","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068922218","display_name":"Gopala K. Anumanchipalli","orcid":"https://orcid.org/0000-0002-9714-7740"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopala Krishna Anumanchipalli","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101768356"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.3735,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62162017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"711","last_page":"718"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9983999729156494,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.6928132772445679},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.6726807951927185},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6137173175811768},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6105246543884277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38473427295684814},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18849122524261475},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16973596811294556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6928132772445679},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.6726807951927185},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6137173175811768},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6105246543884277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38473427295684814},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18849122524261475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16973596811294556},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320315928","display_name":"Rose Hills Foundation","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1965378753","https://openalex.org/W1972620250","https://openalex.org/W1987414756","https://openalex.org/W2068447135","https://openalex.org/W2075570558","https://openalex.org/W2194775991","https://openalex.org/W2231075402","https://openalex.org/W2284050935","https://openalex.org/W2471520273","https://openalex.org/W2593414223","https://openalex.org/W2760103357","https://openalex.org/W2888815552","https://openalex.org/W2888917702","https://openalex.org/W2940585064","https://openalex.org/W2962866891","https://openalex.org/W2964045667","https://openalex.org/W2990440871","https://openalex.org/W3015338123","https://openalex.org/W3015710813","https://openalex.org/W3015721889","https://openalex.org/W3092028330","https://openalex.org/W3095212898","https://openalex.org/W3096429957","https://openalex.org/W3137000704","https://openalex.org/W3159506701","https://openalex.org/W3197273793","https://openalex.org/W4200027410","https://openalex.org/W4220864077","https://openalex.org/W4225956675","https://openalex.org/W4286899907","https://openalex.org/W4292120191","https://openalex.org/W4297841848","https://openalex.org/W4362724041","https://openalex.org/W4372341338","https://openalex.org/W4372348980","https://openalex.org/W4375869034","https://openalex.org/W4390745914","https://openalex.org/W4392902939","https://openalex.org/W4392903427","https://openalex.org/W4399912219","https://openalex.org/W6695676441","https://openalex.org/W6771763809","https://openalex.org/W6782116033","https://openalex.org/W6783867762","https://openalex.org/W6784892142","https://openalex.org/W6791783026","https://openalex.org/W6798451072","https://openalex.org/W6802838302","https://openalex.org/W6810708459","https://openalex.org/W6842057974","https://openalex.org/W6847363464","https://openalex.org/W6870487644"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W2334570605","https://openalex.org/W3181683615","https://openalex.org/W4286826125","https://openalex.org/W1633485514"],"abstract_inverted_index":{"Articulatory":[0],"trajectories":[1],"like":[2],"electromagnetic":[3],"articulography":[4],"(EMA)":[5],"provide":[6],"a":[7,32,59,90,101,110],"low-dimensional":[8,40],"representation":[9],"of":[10,51,107,115,120,148],"the":[11,48,82,126,138,159,165],"vocal":[12],"tract":[13],"filter":[14],"and":[15,62,74,88,109,122,144],"have":[16],"been":[17],"used":[18],"as":[19],"natural,":[20],"grounded":[21],"features":[22,42],"for":[23,35,94],"speech":[24,52,70,147],"synthesis.":[25,37,53],"Differentiable":[26],"digital":[27],"signal":[28],"processing":[29],"(DDSP)":[30],"is":[31,133],"parameter-efficient":[33,63],"framework":[34],"audio":[36],"Therefore,":[38],"integrating":[39],"EMA":[41],"with":[43,117,151],"DDSP":[44,64,131],"can":[45,68,145],"significantly":[46],"enhance":[47],"computational":[49],"efficiency":[50],"In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"fast,":[60],"high-quality,":[61],"articulatory":[65],"vocoder":[66,132],"that":[67],"synthesize":[69],"from":[71],"EMA,":[72],"F0,":[73],"loudness.":[75],"We":[76],"incorporate":[77],"several":[78],"techniques":[79],"to":[80,125,158],"solve":[81],"harmonics":[83],"/":[84],"noise":[85],"imbalance":[86],"problem,":[87],"add":[89],"multiresolution":[91],"adversarial":[92],"loss":[93],"better":[95],"synthesis":[96],"quality.":[97],"Our":[98,130],"model":[99],"achieves":[100],"transcription":[102],"word":[103],"error":[104],"rate":[105],"(WER)":[106],"6.67%":[108],"mean":[111],"opinion":[112],"score":[113],"(MOS)":[114],"3.74,":[116],"an":[118],"improvement":[119],"1.63%":[121],"0.16":[123],"compared":[124],"state-of-the-art":[127],"(SOTA)":[128],"baseline.":[129],"4.9":[134],"x":[135],"faster":[136],"than":[137],"baseline":[139],"on":[140],"CPU":[141],"during":[142],"inference,":[143],"generate":[146],"comparable":[149],"quality":[150],"only":[152],"0.4":[153],"M":[154,161],"parameters,":[155],"in":[156],"contrast":[157],"9":[160],"parameters":[162],"required":[163],"by":[164],"SOTA.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}