{"id":"https://openalex.org/W28591292","doi":"https://doi.org/10.21437/interspeech.2010-423","title":"Fully automatic segmentation for prosodic speech corpora","display_name":"Fully automatic segmentation for prosodic speech corpora","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W28591292","doi":"https://doi.org/10.21437/interspeech.2010-423","mag":"28591292"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-423","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5020460474","display_name":"Sarah Hoffmann","orcid":"https://orcid.org/0000-0001-9549-2594"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Sarah Hoffmann","raw_affiliation_strings":["[ETH, Zurich]"],"affiliations":[{"raw_affiliation_string":"[ETH, Zurich]","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111975528","display_name":"Beat Pfister","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Beat Pfister","raw_affiliation_strings":["[ETH, Zurich]"],"affiliations":[{"raw_affiliation_string":"[ETH, Zurich]","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020460474"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":2.7063,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90169508,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1389","last_page":"1392"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.9968000054359436,"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":0.8591065406799316},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7311251163482666},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7192748188972473},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6495000123977661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6301240921020508},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5942263603210449},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.5704900026321411},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5611239075660706},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5525239109992981},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5251654982566833},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5029265284538269},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46736547350883484},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44302403926849365},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41961032152175903},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.41575223207473755},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4156051278114319},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06666973233222961}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8591065406799316},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7311251163482666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7192748188972473},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6495000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6301240921020508},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5942263603210449},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.5704900026321411},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5611239075660706},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5525239109992981},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5251654982566833},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5029265284538269},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46736547350883484},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44302403926849365},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41961032152175903},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.41575223207473755},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4156051278114319},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06666973233222961},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2010-423","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W153760227","https://openalex.org/W170586818","https://openalex.org/W222076935","https://openalex.org/W1594082249","https://openalex.org/W2054665642","https://openalex.org/W2065796495","https://openalex.org/W2098363562","https://openalex.org/W2148233665","https://openalex.org/W2169711598","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W1965141925","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W2587342322","https://openalex.org/W2161314515"],"abstract_inverted_index":{"While":[0],"automatic":[1,60],"methods":[2,16,57],"for":[3,51,58,116],"phonetic":[4],"segmentation":[5,62,86],"of":[6,13,39,48,84,95],"speech":[7,40,121],"can":[8],"help":[9],"with":[10,99],"rapid":[11],"annotation":[12],"corpora,":[14,111],"most":[15],"rely":[17],"either":[18],"on":[19],"manually":[20],"segmented":[21,69],"data":[22],"to":[23,42,67],"initially":[24,106],"train":[25],"the":[26,46,65,82,89,92,96],"process":[27],"or":[28],"manual":[29],"post-processing.":[30],"This":[31],"is":[32],"very":[33],"time-consuming":[34],"and":[35,70],"slows":[36],"down":[37],"porting":[38],"systems":[41],"new":[43,78],"languages.":[44],"In":[45],"context":[47],"prosody":[49],"corpora":[50,66],"text-to-speech":[52],"(TTS)":[53],"systems,":[54],"we":[55],"investigated":[56],"fully":[59],"phoneme":[61,97],"using":[63],"only":[64],"be":[68],"an":[71],"automatically":[72],"generated":[73],"transcription.":[74],"We":[75,102],"present":[76],"a":[77],"method":[79],"that":[80],"improves":[81],"performance":[83],"HMM-based":[85],"by":[87],"correcting":[88],"boundaries":[90],"between":[91],"training":[93],"stages":[94],"models":[98],"high":[100],"precision.":[101],"show":[103],"that,":[104],"while":[105],"aimed":[107],"at":[108],"single":[109],"speaker":[110],"it":[112],"performs":[113],"equally":[114],"well":[115],"multi-speaker":[117],"corpora.":[118],"Index":[119],"Terms:":[120],"synthesis,":[122],"segmentation,":[123],"boundary":[124],"correction":[125]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}