{"id":"https://openalex.org/W194300377","doi":"https://doi.org/10.21437/interspeech.2004-50","title":"METRIC-SEQDAC: a hybrid approach for audio segmentation","display_name":"METRIC-SEQDAC: a hybrid approach for audio segmentation","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W194300377","doi":"https://doi.org/10.21437/interspeech.2004-50","mag":"194300377"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-50","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-50","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/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hsin-min Wang","raw_affiliation_strings":["Academia Sinica )"],"affiliations":[{"raw_affiliation_string":"Academia Sinica )","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100883805","display_name":"Shih-Sian Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih-sian Cheng","raw_affiliation_strings":["Academia Sinica )"],"affiliations":[{"raw_affiliation_string":"Academia Sinica )","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071214181"],"corresponding_institution_ids":["https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":3.3651,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.9216913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1617","last_page":"1620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9983999729156494,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.993399977684021,"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/segmentation","display_name":"Segmentation","score":0.8233299255371094},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.782317042350769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7587777972221375},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.6491705775260925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5269537568092346},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.5042299032211304},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5013129711151123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39563801884651184},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39399078488349915},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37618035078048706},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08563116192817688}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8233299255371094},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.782317042350769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587777972221375},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.6491705775260925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5269537568092346},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.5042299032211304},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5013129711151123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39563801884651184},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39399078488349915},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37618035078048706},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08563116192817688},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-50","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-50","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W125260059","https://openalex.org/W169282553","https://openalex.org/W1482605500","https://openalex.org/W1499900670","https://openalex.org/W2044591814","https://openalex.org/W2143555316","https://openalex.org/W2153934508","https://openalex.org/W3021773000","https://openalex.org/W3141324706"],"related_works":["https://openalex.org/W2109115373","https://openalex.org/W2390901981","https://openalex.org/W2353818951","https://openalex.org/W1605879311","https://openalex.org/W2611980620","https://openalex.org/W4230691760","https://openalex.org/W2385763735","https://openalex.org/W4391923333","https://openalex.org/W2386394344","https://openalex.org/W3014558862"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,37],"hybrid":[4],"approach":[5,70],"for":[6],"audio":[7,24],"segmentation,":[8],"in":[9],"which":[10],"the":[11,31,43,46,54,72],"metric-based":[12,74],"segmentation":[13,33],"with":[14],"long":[15],"sliding":[16],"windows":[17],"is":[18,34],"applied":[19,35],"first":[20],"to":[21,36,45,51],"segment":[22],"an":[23],"stream":[25],"into":[26],"shorter":[27],"sub-segments,":[28],"and":[29,75],"then":[30],"divide-and-conquer":[32],"fixed-length":[38],"window":[39],"that":[40,68],"slides":[41],"from":[42],"beginning":[44],"end":[47],"of":[48],"each":[49],"sub-segment":[50],"sequentially":[52],"detect":[53],"remaining":[55],"acoustic":[56],"changes.":[57],"The":[58],"experimental":[59],"results":[60],"on":[61],"five":[62],"one-hour":[63],"broadcast":[64],"news":[65],"shows":[66],"show":[67],"our":[69],"outperforms":[71],"existing":[73],"model-selection-based":[76],"approaches.":[77]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
