{"id":"https://openalex.org/W4297841714","doi":"https://doi.org/10.21437/interspeech.2022-10797","title":"WavThruVec: Latent speech representation as intermediate features for neural speech synthesis","display_name":"WavThruVec: Latent speech representation as intermediate features for neural speech synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841714","doi":"https://doi.org/10.21437/interspeech.2022-10797"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10797","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10797","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5087162974","display_name":"Hubert Siuzdak","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hubert Siuzdak","raw_affiliation_strings":["Charactr, Inc"],"affiliations":[{"raw_affiliation_string":"Charactr, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075077837","display_name":"Piotr Dura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piotr Dura","raw_affiliation_strings":["Charactr, Inc"],"affiliations":[{"raw_affiliation_string":"Charactr, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045500067","display_name":"Pol van Rijn","orcid":"https://orcid.org/0000-0002-4044-9123"},"institutions":[{"id":"https://openalex.org/I4210086768","display_name":"Max Planck Institute for Empirical Aesthetics","ror":"https://ror.org/000rdbk18","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210086768"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pol van Rijn","raw_affiliation_strings":["Max-Planck-Institute for Empirical Aesthetics, Frankfurt, Germany"],"affiliations":[{"raw_affiliation_string":"Max-Planck-Institute for Empirical Aesthetics, Frankfurt, Germany","institution_ids":["https://openalex.org/I4210086768"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021757437","display_name":"Nori Jacoby","orcid":"https://orcid.org/0000-0003-2868-0100"},"institutions":[{"id":"https://openalex.org/I4210086768","display_name":"Max Planck Institute for Empirical Aesthetics","ror":"https://ror.org/000rdbk18","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210086768"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nori Jacoby","raw_affiliation_strings":["Max-Planck-Institute for Empirical Aesthetics, Frankfurt, Germany"],"affiliations":[{"raw_affiliation_string":"Max-Planck-Institute for Empirical Aesthetics, Frankfurt, Germany","institution_ids":["https://openalex.org/I4210086768"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087162974"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1852,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89748424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"833","last_page":"837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.8340219259262085},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7199692726135254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6936805248260498},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5812861323356628},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49817347526550293},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4858555495738983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4615267813205719},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.45839226245880127},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4435427486896515},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4420507550239563},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09803923964500427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8340219259262085},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7199692726135254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6936805248260498},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5812861323356628},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49817347526550293},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4858555495738983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4615267813205719},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.45839226245880127},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4435427486896515},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4420507550239563},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09803923964500427},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10797","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10797","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2086381917","https://openalex.org/W2519091744","https://openalex.org/W2766812927","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2974231335","https://openalex.org/W2996286887","https://openalex.org/W3024869864","https://openalex.org/W3026874504","https://openalex.org/W3030437843","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3094550259","https://openalex.org/W3123097577","https://openalex.org/W3123318516","https://openalex.org/W3140429000","https://openalex.org/W3150572638","https://openalex.org/W3161782335","https://openalex.org/W3174758275","https://openalex.org/W3194000401","https://openalex.org/W3198020407","https://openalex.org/W4252978691","https://openalex.org/W4287121924","https://openalex.org/W4287761884","https://openalex.org/W4294619240","https://openalex.org/W4297817572","https://openalex.org/W4394671563"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2595172197","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2084856301","https://openalex.org/W3127543252"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,148],"neural":[3,179],"text-to-speech":[4],"research":[5],"have":[6,51],"been":[7,52],"dominated":[8],"by":[9,83],"two-stage":[10,77],"pipelines":[11],"utilizing":[12],"low-level":[13],"intermediate":[14,90],"speech":[15,91,113],"representation":[16],"such":[17,21,55],"as":[18,89,139,156,158],"mel-spectrograms.":[19],"However,":[20,54],"predetermined":[22],"features":[23],"are":[24,57,102,143],"fundamentally":[25],"limited,":[26],"because":[27],"they":[28,101],"do":[29],"not":[30,172],"allow":[31],"to":[32,59,105,110,119,153,159,163],"exploit":[33],"the":[34,81,121,125,128,169,175],"full":[35],"potential":[36],"of":[37,66,115,177],"a":[38,63,76,116,160],"data-driven":[39],"approach":[40],"through":[41],"learning":[42],"hidden":[43,95],"representations.":[44],"For":[45],"this":[46],"reason,":[47],"several":[48],"end-to-end":[49],"methods":[50],"proposed.":[53],"models":[56],"harder":[58],"train":[60,120],"and":[61],"require":[62],"large":[64],"number":[65],"high-quality":[67],"recordings":[68],"with":[69],"transcriptions.":[70],"Here,":[71],"we":[72],"propose":[73],"WavThruVec":[74],"-":[75],"architecture":[78],"that":[79,168],"resolves":[80],"bottleneck":[82],"using":[84],"high-dimensional":[85],"Wav2Vec":[86,140],"2.0":[87,141],"embeddings":[88,142],"representation.":[92],"Since":[93],"these":[94],"activations":[96],"provide":[97],"high-level":[98],"linguistic":[99],"features,":[100],"more":[103],"robust":[104],"noise.":[106],"That":[107],"allows":[108],"us":[109],"utilize":[111],"annotated":[112],"datasets":[114],"lower":[117],"quality":[118,176],"first-stage":[122],"module.":[123],"At":[124],"same":[126],"time,":[127],"second-stage":[129],"component":[130],"can":[131],"be":[132],"trained":[133],"on":[134],"large-scale":[135],"untranscribed":[136],"audio":[137],"corpora,":[138],"already":[144],"time-aligned.":[145],"This":[146],"results":[147],"an":[149],"increased":[150],"generalization":[151,162],"capability":[152],"out-of-vocabulary":[154],"words,":[155],"well":[157],"better":[161],"unseen":[164],"speakers.":[165],"We":[166],"show":[167],"proposed":[170],"model":[171],"only":[173],"matches":[174],"state-of-the-art":[178],"models,":[180],"but":[181],"also":[182],"presents":[183],"useful":[184],"properties":[185],"enabling":[186],"tasks":[187],"like":[188],"voice":[189],"conversion":[190],"or":[191],"zero-shot":[192],"synthesis.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-10-01T00:00:00"}