{"id":"https://openalex.org/W79237494","doi":"https://doi.org/10.21437/interspeech.2004-477","title":"Statistical corpus-based speech segmentation","display_name":"Statistical corpus-based speech segmentation","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W79237494","doi":"https://doi.org/10.21437/interspeech.2004-477","mag":"79237494"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-477","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5001028439","display_name":"Vincent Pollet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Pollet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013822007","display_name":"Geert Coorman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geert Coorman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4626,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72983522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1929","last_page":"1932"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.9891999959945679,"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/segmentation","display_name":"Segmentation","score":0.7903895378112793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7773745059967041},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7470521330833435},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.6782809495925903},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5987558364868164},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5943259596824646},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5830376148223877},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.5692868232727051},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5573508143424988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5281486511230469},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5004520416259766},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.45071399211883545},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4468734860420227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4420846104621887},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1259666383266449}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7903895378112793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773745059967041},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7470521330833435},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.6782809495925903},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5987558364868164},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5943259596824646},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5830376148223877},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.5692868232727051},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5573508143424988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5281486511230469},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5004520416259766},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.45071399211883545},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4468734860420227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4420846104621887},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1259666383266449},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-477","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W85160440","https://openalex.org/W88703138","https://openalex.org/W88973946","https://openalex.org/W114226241","https://openalex.org/W156258841","https://openalex.org/W1550297032","https://openalex.org/W1846623966","https://openalex.org/W2397554020"],"related_works":["https://openalex.org/W2347413598","https://openalex.org/W2330863229","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W114226241"],"abstract_inverted_index":{"An":[0],"automatic":[1,100],"speech":[2,16,24,32,50,59],"segmentation":[3,102,118],"technique":[4,107],"is":[5,8,44,68,113],"presented":[6],"that":[7,35],"based":[9],"on":[10],"the":[11,48,65,90,106],"alignment":[12],"of":[13,21,64,73,108],"a":[14,19,28,71],"target":[15,49,66],"signal":[17,43,67],"with":[18],"set":[20],"different":[22,57],"reference":[23,42,58],"signals":[25],"generated":[26],"by":[27,70],"specific":[29],"designed":[30],"corpus-based":[31],"synthesis":[33],"system":[34],"additionally":[36],"generates":[37],"phoneme":[38,62,75,101],"boundary":[39,63,76,79],"markers.":[40],"Each":[41],"then":[45],"warped":[46,74],"to":[47,88,97],"signal.":[51],"By":[52],"synthesizing":[53],"and":[54,83,99],"warping":[55],"many":[56],"signals,":[60],"each":[61],"characterized":[69],"distribution":[72],"positions.":[77],"The":[78],"distributions":[80],"are":[81,103,120],"statistically":[82],"acoustically":[84],"processed":[85],"in":[86],"order":[87],"generate":[89],"final":[91],"segmentation.":[92],"First,":[93],"some":[94],"problems":[95],"related":[96],"manual":[98],"addressed.":[104],"Then":[105],"Statistical":[109],"Corpus-based":[110],"Segmentation":[111],"(SCS)":[112],"introduced.":[114],"Finally,":[115],"intraand":[116],"inter-speaker":[117],"results":[119],"presented.":[121]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
