{"id":"https://openalex.org/W2057752423","doi":"https://doi.org/10.1109/icassp.2009.4960525","title":"Effective metric-based speaker segmentation in the frequency domain","display_name":"Effective metric-based speaker segmentation in the frequency domain","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2057752423","doi":"https://doi.org/10.1109/icassp.2009.4960525","mag":"2057752423"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055045322","display_name":"Christoph Boehm","orcid":"https://orcid.org/0000-0001-7358-6709"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Christoph Boehm","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria#TAB#","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015798259","display_name":"Franz Pernkopf","orcid":"https://orcid.org/0000-0002-6356-3367"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Franz Pernkopf","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria#TAB#","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":0.6453,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59792818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4081","last_page":"4084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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":0.9911999702453613,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9520999789237976,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.8785947561264038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7194521427154541},{"id":"https://openalex.org/keywords/constant-false-alarm-rate","display_name":"Constant false alarm rate","score":0.6739230751991272},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6502482295036316},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6268891096115112},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5797547698020935},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5044912099838257},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48394137620925903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46845555305480957},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.46286994218826294},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4159639775753021},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.41279342770576477},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.4105331003665924},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.19392570853233337},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13493558764457703}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8785947561264038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7194521427154541},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.6739230751991272},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6502482295036316},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6268891096115112},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5797547698020935},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5044912099838257},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48394137620925903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46845555305480957},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.46286994218826294},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4159639775753021},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.41279342770576477},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.4105331003665924},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.19392570853233337},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13493558764457703},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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":5,"referenced_works":["https://openalex.org/W1999405202","https://openalex.org/W2044591814","https://openalex.org/W2099111195","https://openalex.org/W2159591770","https://openalex.org/W3159930100"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W3164669818","https://openalex.org/W1573546415","https://openalex.org/W2906993205","https://openalex.org/W1983393909","https://openalex.org/W2040150569","https://openalex.org/W2468095590","https://openalex.org/W2132174924","https://openalex.org/W1911540634","https://openalex.org/W2013909972"],"abstract_inverted_index":{"In":[0,71],"this":[1],"paper,":[2],"we":[3],"present":[4],"an":[5],"approach,":[6],"called":[7],"FREQDIST,":[8],"for":[9,73],"speaker":[10],"segmentation":[11,59],"based":[12,41],"on":[13,42],"a":[14,62,80,96],"distance":[15],"measurement":[16],"applied":[17],"in":[18],"the":[19,24,27,43,47,67,74,89,92],"frequency":[20],"domain.":[21],"To":[22],"enhance":[23],"detection":[25,98],"performance,":[26],"spectrum":[28],"is":[29],"reweighted":[30],"using":[31,46],"normalization":[32],"techniques.":[33],"Additionally,":[34],"noise-like":[35],"(i.e.":[36],"flat)":[37],"spectra":[38],"are":[39],"removed":[40],"entropy.":[44],"Experiments":[45],"TIMIT":[48,75],"database":[49],"[1]":[50],"and":[51,95],"Westdeutscher":[52],"Rundfunk":[53],"broadcast":[54],"data":[55,76],"show":[56],"that":[57],"our":[58,77],"approach":[60],"yields":[61],"good":[63],"performance":[64],"compared":[65],"to":[66],"DISTBIC":[68,93],"algorithm":[69,78,94],"[2].":[70],"particular,":[72],"reaches":[79],"false":[81],"alarm":[82],"rate":[83,99],"(FAR)":[84],"less":[85],"than":[86],"half":[87],"of":[88,91,101,104],"value":[90],"missed":[97],"(MDR)":[100],"7.0%":[102],"instead":[103],"13.1%.":[105]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}