{"id":"https://openalex.org/W2937881934","doi":"https://doi.org/10.1109/icassp.2019.8683846","title":"Casting to Corpus: Segmenting and Selecting Spontaneous Dialogue for Tts with a Cnn-lstm Speaker-dependent Breath Detector","display_name":"Casting to Corpus: Segmenting and Selecting Spontaneous Dialogue for Tts with a Cnn-lstm Speaker-dependent Breath Detector","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937881934","doi":"https://doi.org/10.1109/icassp.2019.8683846","mag":"2937881934"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5063795282","display_name":"\u00c9va Sz\u00e9kely","orcid":"https://orcid.org/0000-0003-1175-840X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Eva Szekely","raw_affiliation_strings":["Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015417808","display_name":"Joakim Gustafson","orcid":"https://orcid.org/0000-0002-0397-6442"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Joakim Gustafson","raw_affiliation_strings":["Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063795282"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":2.3803,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91260364,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6925","last_page":"6929"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9930999875068665,"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":0.7782751321792603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7448707818984985},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5573519468307495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4830785095691681},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4800035357475281},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.47591549158096313},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46082744002342224},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.41275668144226074},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.366796612739563},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31507107615470886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782751321792603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7448707818984985},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5573519468307495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4830785095691681},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4800035357475281},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.47591549158096313},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46082744002342224},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.41275668144226074},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.366796612739563},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31507107615470886},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1592103878","https://openalex.org/W2001607878","https://openalex.org/W2047359386","https://openalex.org/W2085843736","https://openalex.org/W2126326123","https://openalex.org/W2129142580","https://openalex.org/W2163605009","https://openalex.org/W2296111744","https://openalex.org/W2317015831","https://openalex.org/W2405144467","https://openalex.org/W2406713305","https://openalex.org/W2570199661","https://openalex.org/W2578321825","https://openalex.org/W2586482422","https://openalex.org/W2614550605","https://openalex.org/W2742272018","https://openalex.org/W2746419079","https://openalex.org/W2748900206","https://openalex.org/W2765860599","https://openalex.org/W2791846162","https://openalex.org/W2795023788","https://openalex.org/W2891460598","https://openalex.org/W2916979304","https://openalex.org/W2964195110","https://openalex.org/W6635546818","https://openalex.org/W6684191040","https://openalex.org/W6697477453","https://openalex.org/W6713701993","https://openalex.org/W6732215457","https://openalex.org/W6749598711","https://openalex.org/W7027867769"],"related_works":["https://openalex.org/W4214896311","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"This":[0,120],"paper":[1],"considers":[2],"utilising":[3],"breaths":[4],"to":[5,28,55,75,100],"create":[6],"improved":[7],"spontaneous-speech":[8],"corpora":[9],"for":[10,94,133],"conversational":[11],"text-to-speech":[12],"from":[13],"found":[14],"audio":[15,106],"recordings":[16],"such":[17],"as":[18],"dialogue":[19],"podcasts.":[20],"Breaths":[21],"are":[22,34,115],"of":[23,36,49,103,113],"interest":[24],"since":[25],"they":[26],"relate":[27],"prosody":[29],"and":[30,33,38,59,67,85,117,128],"speech":[31],"planning":[32],"independent":[35],"language":[37],"transcription.":[39],"Specifically,":[40],"we":[41],"propose":[42],"a":[43,47,57,95,122],"semi-supervised":[44],"approach":[45],"where":[46],"fraction":[48],"coarsely":[50],"annotated":[51],"data":[52],"is":[53,73],"used":[54,74],"train":[56],"convolutional":[58],"recurrent":[60],"speaker-specific":[61],"breath":[62,78],"detector":[63],"operating":[64],"on":[65],"spectrograms":[66],"zero-crossing":[68],"rate.":[69],"The":[70],"classifier":[71],"output":[72],"find":[76],"target-speaker":[77],"groups":[79],"(audio":[80],"segments":[81],"delineated":[82],"by":[83],"breaths)":[84],"subsequently":[86],"select":[87],"those":[88],"that":[89,124],"constitute":[90],"clean":[91,116],"utterances":[92,109],"appropriate":[93],"synthesis":[96],"corpus.":[97],"An":[98],"application":[99],"11":[101],"hours":[102],"raw":[104],"podcast":[105],"extracts":[107],"1969":[108],"(106":[110],"minutes),":[111],"87%":[112],"which":[114],"correctly":[118],"segmented.":[119],"outperforms":[121],"baseline":[123],"performs":[125],"integrated":[126],"VAD":[127],"speaker":[129],"attribution":[130],"without":[131],"accounting":[132],"breaths.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}