{"id":"https://openalex.org/W4385823488","doi":"https://doi.org/10.21437/interspeech.2023-1978","title":"Evaluating and reducing the distance between synthetic and real speech distributions","display_name":"Evaluating and reducing the distance between synthetic and real speech distributions","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823488","doi":"https://doi.org/10.21437/interspeech.2023-1978"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1978","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/370165522/Evaluating_and_reducing_MINIXHOFER_DOA17052023_AFV_CC_BY.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086910199","display_name":"Christoph Minixhofer","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Christoph Minixhofer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044666169","display_name":"Ond\u0159ej Klejch","orcid":"https://orcid.org/0000-0001-5495-967X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ond\u0159ej Klejch","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086910199"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3682,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59792521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2078","last_page":"2082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9742000102996826,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9742000102996826,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9740999937057495,"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":0.9575999975204468,"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":0.662021279335022},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5437769293785095},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43790823221206665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3225545585155487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.662021279335022},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5437769293785095},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43790823221206665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3225545585155487}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-1978","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/a2f72b47-a06d-4bbf-a100-759826439b3f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a2f72b47-a06d-4bbf-a100-759826439b3f","pdf_url":"https://www.research.ed.ac.uk/files/370165522/Evaluating_and_reducing_MINIXHOFER_DOA17052023_AFV_CC_BY.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Minixhofer, C, Klejch, O & Bell, P 2023, Evaluating and reducing the distance between synthetic and real speech distributions. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 2078-2082, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-1978","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/a2f72b47-a06d-4bbf-a100-759826439b3f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a2f72b47-a06d-4bbf-a100-759826439b3f","pdf_url":"https://www.research.ed.ac.uk/files/370165522/Evaluating_and_reducing_MINIXHOFER_DOA17052023_AFV_CC_BY.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Minixhofer, C, Klejch, O & Bell, P 2023, Evaluating and reducing the distance between synthetic and real speech distributions. in Proc. INTERSPEECH 2023. Interspeech, International Speech Communication Association, pp. 2078-2082, Interspeech 2023, Dublin, Ireland, 20/08/23. https://doi.org/10.21437/Interspeech.2023-1978","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823488.pdf","grobid_xml":"https://content.openalex.org/works/W4385823488.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W127416991"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"Automatic":[2],"Speech":[3],"Recognition":[4],"(ASR)":[5],"has":[6,36],"gained":[7],"popularity":[8],"in":[9,33,48,130],"recent":[10],"years,":[11],"with":[12],"most":[13],"research":[14],"focusing":[15],"on":[16,53,86],"designing":[17],"novel":[18],"neural":[19],"network":[20],"architectures,":[21],"speech":[22],"rep":[23],"resentations,":[24],"and":[25,61,74,90,103],"loss":[26],"functions.":[27],"However,":[28],"the":[29,54,65,75,105,121,131],"importance":[30],"of":[31,44,67,77,123,133],"topology":[32,45,112],"E2E":[34,134],"ASR":[35,135],"been":[37],"largely":[38],"neglected.":[39],"There":[40],"are":[41],"many":[42],"aspects":[43],"to":[46],"consider;":[47],"this":[49],"paper,":[50],"we":[51],"focus":[52],"relationship":[55],"between":[56],"topologies\u2019":[57],"minimum":[58],"traversal":[59],"time":[60],"output":[62,72],"frame":[63,97],"rate,":[64],"number":[66],"distinct":[68],"states":[69],"for":[70],"each":[71],"unit,":[73],"flexibility":[76],"alignments":[78],"admitted.":[79],"We":[80],"ex":[81],"amine":[82],"several":[83],"different":[84,96],"topologies":[85,102],"two":[87],"datasets:":[88],"WSJ":[89],"Librispeech.":[91],"Our":[92,117],"experiments":[93],"reveal":[94],"that":[95,104,120],"rates":[98],"have":[99],"varying":[100],"optimal":[101],"commonly":[106],"used":[107],"Connectionist":[108],"Temporal":[109],"Classification":[110],"(CTC)":[111],"is":[113,126],"not":[114],"always":[115],"optimal.":[116],"findings":[118],"suggest":[119],"choice":[122],"topol":[124],"ogy":[125],"an":[127],"important":[128],"consideration":[129],"design":[132],"systems.<br/><br/>":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}
