{"id":"https://openalex.org/W4415432841","doi":"https://doi.org/10.21437/interspeech.2025-2190","title":"Towards Frame-level Quality Predictions of Synthetic Speech","display_name":"Towards Frame-level Quality Predictions of Synthetic Speech","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432841","doi":"https://doi.org/10.21437/interspeech.2025-2190"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2190","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.10374","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009710583","display_name":"Michael Kuhlmann","orcid":"https://orcid.org/0000-0003-3664-6922"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Michael Kuhlmann","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022762565","display_name":"Fritz Seebauer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fritz Seebauer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070024202","display_name":"Petra Wagner","orcid":"https://orcid.org/0000-0001-6662-3612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petra Wagner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009710583"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2845,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9128424,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2300","last_page":"2304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9894999861717224,"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":0.9894999861717224,"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/quality","display_name":"Quality (philosophy)","score":0.715399980545044},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6183000206947327},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5989000201225281},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5777000188827515},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5447999835014343},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.5192999839782715},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5148000121116638},{"id":"https://openalex.org/keywords/quality-score","display_name":"Quality Score","score":0.46959999203681946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717199981212616},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.715399980545044},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6183000206947327},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5989000201225281},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5777000188827515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5590000152587891},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5478000044822693},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.5192999839782715},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.46959999203681946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4350999891757965},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3864000141620636},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2190","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.10374","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.10374","pdf_url":"https://arxiv.org/pdf/2508.10374","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":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.10374","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.10374","pdf_url":"https://arxiv.org/pdf/2508.10374","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":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"automatic":[1,16],"subjective":[2],"speech":[3,37],"quality":[4,17,53,107],"assessment":[5,18,35],"has":[6],"witnessed":[7],"much":[8],"progress,":[9],"an":[10,15],"open":[11],"question":[12],"is":[13,22],"whether":[14],"at":[19],"frame":[20],"resolution":[21],"possible.":[23],"This":[24],"would":[25],"be":[26],"highly":[27],"desirable,":[28],"as":[29],"it":[30],"adds":[31],"explainability":[32],"to":[33],"the":[34,78,85,99],"of":[36,51,80,87,102,105,117],"synthesis":[38],"systems.":[39],"Here,":[40],"we":[41,61,91],"take":[42],"first":[43],"steps":[44],"towards":[45],"this":[46],"goal":[47],"by":[48],"identifying":[49],"issues":[50],"existing":[52],"predictors":[54,108],"that":[55,64,76,111],"prevent":[56],"sensible":[57],"frame-level":[58,66,106],"prediction.":[59],"Further,":[60],"define":[62],"criteria":[63],"a":[65,73,81,103,122],"predictor":[67],"should":[68],"fulfill.":[69],"We":[70],"also":[71],"suggest":[72],"chunk-based":[74],"processing":[75],"avoids":[77],"impact":[79],"localized":[82,96],"distortion":[83],"on":[84],"score":[86],"neighboring":[88],"frames.":[89],"Finally,":[90],"measure":[92],"in":[93],"experiments":[94],"with":[95],"artificial":[97],"distortions":[98],"localization":[100],"performance":[101,116],"set":[104],"and":[109],"show":[110],"they":[112],"can":[113],"outperform":[114],"detection":[115],"human":[118],"annotations":[119],"obtained":[120],"from":[121],"crowd-sourced":[123],"perception":[124],"experiment.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-23T00:00:00"}