{"id":"https://openalex.org/W2168417340","doi":"https://doi.org/10.1109/isspa.2007.4555471","title":"Segmentation and its real-world applications in speech processing","display_name":"Segmentation and its real-world applications in speech processing","publication_year":2007,"publication_date":"2007-02-01","ids":{"openalex":"https://openalex.org/W2168417340","doi":"https://doi.org/10.1109/isspa.2007.4555471","mag":"2168417340"},"language":"en","primary_location":{"id":"doi:10.1109/isspa.2007.4555471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2007.4555471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 9th International Symposium on Signal Processing and Its Applications","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/A5018853653","display_name":"Farook Sattar","orcid":"https://orcid.org/0000-0001-6272-3982"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Farook Sattar","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103376730","display_name":"Mikael Nilsson","orcid":null},"institutions":[{"id":"https://openalex.org/I52719799","display_name":"Blekinge Institute of Technology","ror":"https://ror.org/0093a8w51","country_code":"SE","type":"education","lineage":["https://openalex.org/I52719799"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mikael Nilsson","raw_affiliation_strings":["School of Engineering, Blekinge Institute of Technology, Ronneby, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Blekinge Institute of Technology, Ronneby, Sweden","institution_ids":["https://openalex.org/I52719799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052616489","display_name":"Ingvar Claesson","orcid":null},"institutions":[{"id":"https://openalex.org/I52719799","display_name":"Blekinge Institute of Technology","ror":"https://ror.org/0093a8w51","country_code":"SE","type":"education","lineage":["https://openalex.org/I52719799"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ingvar Claesson","raw_affiliation_strings":["School of Engineering, Blekinge Institute of Technology, Ronneby, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Blekinge Institute of Technology, Ronneby, Sweden","institution_ids":["https://openalex.org/I52719799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"81","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9979000091552734,"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/speech-recognition","display_name":"Speech recognition","score":0.7871127128601074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7858061194419861},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7619503736495972},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.720354437828064},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7071871161460876},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6680843234062195},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.6101908087730408},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5362483859062195},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4728163480758667},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.4592364728450775},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4454272985458374},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.44158482551574707},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.43770965933799744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34929925203323364},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.11024370789527893}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7871127128601074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858061194419861},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7619503736495972},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.720354437828064},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7071871161460876},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6680843234062195},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.6101908087730408},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5362483859062195},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4728163480758667},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.4592364728450775},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4454272985458374},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.44158482551574707},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.43770965933799744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34929925203323364},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.11024370789527893},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isspa.2007.4555471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2007.4555471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 9th International Symposium on Signal Processing and Its Applications","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":13,"referenced_works":["https://openalex.org/W1493163583","https://openalex.org/W1506809288","https://openalex.org/W1546892833","https://openalex.org/W1578953027","https://openalex.org/W1965392255","https://openalex.org/W1970352604","https://openalex.org/W2029027380","https://openalex.org/W2033493106","https://openalex.org/W2034139177","https://openalex.org/W2100555417","https://openalex.org/W2127836593","https://openalex.org/W2130739159","https://openalex.org/W2156038773"],"related_works":["https://openalex.org/W2159307410","https://openalex.org/W4319347033","https://openalex.org/W1542588102","https://openalex.org/W1890431648","https://openalex.org/W2020464095","https://openalex.org/W2151333624","https://openalex.org/W1572861854","https://openalex.org/W1987001738","https://openalex.org/W1968776176","https://openalex.org/W1591426470"],"abstract_inverted_index":{"The":[0,44,56,85],"speech":[1,14,21,40,54,74,97],"segmentation":[2,31],"problem":[3],"can":[4],"be":[5],"formulated":[6],"as":[7],"estimating":[8],"the":[9,19,67,73,96,101,106,109],"locations":[10],"and":[11,15,33,104],"durations":[12],"of":[13,18,35,52,108],"non-speech":[16,79],"components":[17,80],"measured":[20],"data.":[22,55],"In":[23],"this":[24],"paper,":[25],"a":[26,50],"new":[27],"time-scale":[28],"transform":[29],"based":[30],"method":[32,68,86],"one":[34],"its":[36],"important":[37],"application":[38],"in":[39,95,100],"processing,":[41],"are":[42,59],"presented.":[43],"proposed":[45],"scheme":[46],"is":[47,64,69],"tested":[48],"on":[49],"number":[51],"recorded":[53],"preliminary":[57],"results":[58],"shown":[60],"quite":[61],"promising.":[62],"It":[63],"found":[65],"that":[66],"able":[70],"to":[71,91],"extract":[72],"components(i.e.":[75],"active":[76],"intervals)":[77,83],"from":[78],"(i.e.":[81],"inactive":[82],"effectively.":[84],"is,":[87],"therefore,":[88],"successfully":[89],"applied":[90],"insert":[92],"selective":[93],"pauses":[94],"before":[98],"delivering":[99],"reverberant":[102],"environment":[103],"improve":[105],"quality/intelligibility":[107],"delivered":[110],"speech.":[111]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
