{"id":"https://openalex.org/W3045354608","doi":"https://doi.org/10.21437/interspeech.2020-1323","title":"Multi-Speaker Emotion Conversion via Latent Variable Regularization and a Chained Encoder-Decoder-Predictor Network","display_name":"Multi-Speaker Emotion Conversion via Latent Variable Regularization and a Chained Encoder-Decoder-Predictor Network","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3045354608","doi":"https://doi.org/10.21437/interspeech.2020-1323","mag":"3045354608"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1323","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.12937","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101998305","display_name":"Ravi Shankar","orcid":"https://orcid.org/0000-0002-4882-3159"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ravi Shankar","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068532249","display_name":"Hsi-Wei Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsi-Wei Hsieh","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064933293","display_name":"Nicolas Charon","orcid":"https://orcid.org/0000-0002-6032-247X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolas Charon","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083233304","display_name":"Archana Venkataraman","orcid":"https://orcid.org/0000-0003-2653-5591"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Archana Venkataraman","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101998305"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.7619,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70974285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3391","last_page":"3395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9943000078201294,"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/computer-science","display_name":"Computer science","score":0.7500194311141968},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6627975106239319},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6345161199569702},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6102955937385559},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.528237521648407},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4939773678779602},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.49395638704299927},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48389777541160583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4696734845638275},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.44009652733802795},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43159353733062744},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3533628582954407},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3414885401725769},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18810150027275085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500194311141968},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6627975106239319},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6345161199569702},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6102955937385559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.528237521648407},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4939773678779602},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.49395638704299927},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48389777541160583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4696734845638275},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.44009652733802795},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43159353733062744},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3533628582954407},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3414885401725769},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18810150027275085},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1323","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.12937","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.12937","pdf_url":"https://arxiv.org/pdf/2007.12937","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2007.12937","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.12937","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3045354608","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.12937","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.12937","pdf_url":"https://arxiv.org/pdf/2007.12937","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3045354608.pdf","grobid_xml":"https://content.openalex.org/works/W3045354608.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W112588824","https://openalex.org/W586270867","https://openalex.org/W1976725440","https://openalex.org/W2006302620","https://openalex.org/W2049686551","https://openalex.org/W2077801020","https://openalex.org/W2115167851","https://openalex.org/W2170167891","https://openalex.org/W2471520273","https://openalex.org/W2517513811","https://openalex.org/W2519091744","https://openalex.org/W2766406951","https://openalex.org/W2774848319","https://openalex.org/W2786270934","https://openalex.org/W2948238043","https://openalex.org/W2962793481","https://openalex.org/W2963091184","https://openalex.org/W2963684088","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2972334330","https://openalex.org/W2972366998","https://openalex.org/W2973138167","https://openalex.org/W2976159681","https://openalex.org/W2981934523","https://openalex.org/W3004402693"],"related_works":["https://openalex.org/W3097962967","https://openalex.org/W2962891349","https://openalex.org/W2501088019","https://openalex.org/W3111110720","https://openalex.org/W2898421198","https://openalex.org/W2962678076","https://openalex.org/W2039089492","https://openalex.org/W2929650096","https://openalex.org/W2970758893","https://openalex.org/W2940887868","https://openalex.org/W2943586321","https://openalex.org/W3123267973","https://openalex.org/W3121491896","https://openalex.org/W75324424","https://openalex.org/W3184148807","https://openalex.org/W2958654481","https://openalex.org/W3200590977","https://openalex.org/W2791756768","https://openalex.org/W3152804956","https://openalex.org/W3126131691"],"abstract_inverted_index":{"We":[0,91],"propose":[1],"a":[2,12,21,57,75],"novel":[3],"method":[4,95],"for":[5,134],"emotion":[6,106],"conversion":[7,107],"in":[8,56,129],"speech":[9],"based":[10],"on":[11,101],"chained":[13],"encoder-decoder-predictor":[14],"neural":[15],"network":[16],"architecture.":[17],"The":[18,45],"encoder":[19],"constructs":[20],"latent":[22],"embedding":[23,49],"of":[24,87,105,111],"the":[25,31,37,52,62,65,69,85,97,103,109,116],"fundamental":[26],"frequency":[27],"(F0)":[28],"contour":[29,55,72],"and":[30,68,108],"spectrum,":[32],"which":[33],"we":[34],"regularize":[35],"using":[36],"Large":[38],"Diffeomorphic":[39],"Metric":[40],"Mapping":[41],"(LDDMM)":[42],"registration":[43],"framework.":[44],"decoder":[46],"uses":[47,64],"this":[48],"to":[50,73,122],"predict":[51],"modified":[53,70],"F0":[54,71],"target":[58,77],"emotional":[59],"class.":[60],"Finally,":[61],"predictor":[63],"original":[66],"spectrum":[67],"generate":[74],"corresponding":[76],"spectrum.":[78],"Our":[79],"joint":[80],"objective":[81],"function":[82],"simultaneously":[83],"optimizes":[84],"parameters":[86],"three":[88],"model":[89,121],"blocks.":[90],"show":[92],"that":[93,125],"our":[94,120],"outperforms":[96],"existing":[98],"state-of-the-art":[99],"approaches":[100],"both,":[102],"saliency":[104],"quality":[110],"resynthesized":[112],"speech.":[113],"In":[114],"addition,":[115],"LDDMM":[117],"regularization":[118],"allows":[119],"convert":[123],"phrases":[124],"were":[126],"not":[127],"present":[128],"training,":[130],"thus":[131],"providing":[132],"evidence":[133],"out-of-sample":[135],"generalization.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}