{"id":"https://openalex.org/W92552095","doi":"https://doi.org/10.21437/interspeech.2005-572","title":"Phonetic labeling and segmentation of mixed-lingual prosody databases","display_name":"Phonetic labeling and segmentation of mixed-lingual prosody databases","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W92552095","doi":"https://doi.org/10.21437/interspeech.2005-572","mag":"92552095"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-572","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5032097217","display_name":"Harald Romsdorfer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088543","display_name":"Institut f\u00fcr Informationsverarbeitung","ror":"https://ror.org/0047j9t38","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210088543"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Harald Romsdorfer","raw_affiliation_strings":["Institut f\u00fcr Signalverarbeitung und Sprachkommunikation (4420)"],"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Signalverarbeitung und Sprachkommunikation (4420)","institution_ids":["https://openalex.org/I4210088543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111975528","display_name":"Beat Pfister","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beat Pfister","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032097217"],"corresponding_institution_ids":["https://openalex.org/I4210088543"],"apc_list":null,"apc_paid":null,"fwci":0.8775,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78351344,"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":"3281","last_page":"3284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9977999925613403,"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/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"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":0.7875145077705383},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7675106525421143},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7265080213546753},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6914440393447876},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6279545426368713},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6063919067382812},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5981210470199585},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.5951272249221802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5456326007843018},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5114563703536987},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.46363112330436707},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4323042035102844},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.41119492053985596},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3071611225605011},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0819786787033081}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875145077705383},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7675106525421143},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7265080213546753},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6914440393447876},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6279545426368713},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6063919067382812},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5981210470199585},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.5951272249221802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5456326007843018},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5114563703536987},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.46363112330436707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4323042035102844},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.41119492053985596},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3071611225605011},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0819786787033081},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2005-572","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W45136203","https://openalex.org/W97413234","https://openalex.org/W146439846","https://openalex.org/W170354295","https://openalex.org/W205593963","https://openalex.org/W2033037901","https://openalex.org/W2509504569"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2161314515"],"abstract_inverted_index":{"An":[0],"automatic":[1],"system":[2,23,40],"for":[3,8,86],"segmenting":[4],"speech":[5,47],"signals":[6,48],"used":[7],"the":[9,22,31,39,46,50,76,80],"training":[10,74],"of":[11,49,56,79],"statistical":[12],"prosody":[13,51],"models":[14],"is":[15,41,93,97],"presented.":[16],"Starting":[17],"from":[18],"a":[19,57],"canonical":[20,77],"transcription,":[21],"simultaneously":[24],"delivers":[25],"an":[26],"accurate":[27],"phonetic":[28,33],"segmentation":[29],"and":[30,90],"matched":[32],"transcription":[34],"indicating":[35],"pronunciation":[36,88],"variants.":[37],"Although":[38],"HMM-based,":[42],"it":[43],"uses":[44],"only":[45],"database":[52],"which":[53],"typically":[54],"consists":[55],"few":[58],"hundred":[59],"sentences":[60],"with":[61,72],"some":[62],"30":[63],"minutes":[64],"total":[65],"duration.":[66],"Initial":[67],"phone":[68],"HMMs":[69],"are":[70],"generated":[71],"flat-start":[73],"using":[75],"transcriptions":[78],"sentences.":[81],"Then":[82],"iterative":[83],"Viterbi":[84],"search":[85],"best-matching":[87],"variants":[89],"HMM":[91],"retraining":[92],"applied":[94],"until":[95],"convergence":[96],"attained.":[98]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}