{"id":"https://openalex.org/W1509818672","doi":"https://doi.org/10.21437/interspeech.2006-463","title":"Speech/non-speech discrimination combining advanced feature extraction and SVM learning","display_name":"Speech/non-speech discrimination combining advanced feature extraction and SVM learning","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W1509818672","doi":"https://doi.org/10.21437/interspeech.2006-463","mag":"1509818672"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-463","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5067023995","display_name":"Javier Ram\u0131\u0301rez","orcid":"https://orcid.org/0000-0002-6229-2921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Ram\u00edrez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019063260","display_name":"Pablo Y\u00e9lamos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pablo Y\u00e9lamos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011354002","display_name":"J. M. G\u00f3rriz","orcid":"https://orcid.org/0000-0001-7069-1714"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. M. G\u00f3rriz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000645757","display_name":"Jos\u00e9 C. Segura","orcid":"https://orcid.org/0000-0003-3746-0978"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jos\u00e9 C. Segura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113239329","display_name":"L. Garc\u0131\u0301a","orcid":"https://orcid.org/0000-0002-2788-8930"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L. Garc\u00eda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3234,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.52684099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"paper 1134","last_page":"Wed1FoP.3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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":0.751306414604187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.693060040473938},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6817731261253357},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6701014637947083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5580971837043762},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4111334979534149}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751306414604187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.693060040473938},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6817731261253357},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6701014637947083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5580971837043762},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4111334979534149}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2006-463","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.76.7226","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.76.7226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sirio.ugr.es/segura/pdfdocs/IS2006c.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.99.1261","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.99.1261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cvsp.cs.ntua.gr/projects/pub/HIWIRE/HiwirePublications/javiercslp06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1503480726","https://openalex.org/W1604938182","https://openalex.org/W1979012094","https://openalex.org/W2032362923","https://openalex.org/W2101357962","https://openalex.org/W2115717467","https://openalex.org/W2129120544","https://openalex.org/W2132470613","https://openalex.org/W2148603752","https://openalex.org/W2153635508","https://openalex.org/W2156038773","https://openalex.org/W2407641997","https://openalex.org/W2541377018"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W2601157893","https://openalex.org/W2131735617","https://openalex.org/W2373006798","https://openalex.org/W2056912418","https://openalex.org/W2123759770","https://openalex.org/W2151520854","https://openalex.org/W2033213769","https://openalex.org/W4312376745"],"abstract_inverted_index":{"This":[0],"paper":[1],"shows":[2,122],"an":[3,32,86],"effective":[4,87],"speech/non-speech":[5,104],"discrimination":[6,105],"method":[7,22],"for":[8,136],"improving":[9],"the":[10,66,69,75,80,118],"performance":[11],"of":[12,40,68],"speech":[13,41,138,155],"processing":[14],"systems":[15],"working":[16],"in":[17],"noisy":[18],"environment.":[19],"The":[20,112],"proposed":[21],"uses":[23],"a":[24,96],"trained":[25],"support":[26,151],"vector":[27,98,152],"machine":[28,153],"(SVM)":[29],"that":[30,95],"defines":[31],"optimized":[33],"non-linear":[34,88],"decision":[35,89],"rule":[36],"over":[37,125],"different":[38],"sets":[39],"features.":[42],"Two":[43],"alternative":[44],"feature":[45,97],"extraction":[46],"processes":[47],"based":[48],"on:":[49],"i)":[50],"subband":[51],"SNR":[52,59],"estimation":[53,60],"after":[54],"denoising,":[55],"and":[56,83,133,141],"ii)":[57],"long-term":[58],"were":[61],"compared.":[62],"Both":[63],"methods":[64],"show":[65],"ability":[67],"SVM-based":[70],"classifier":[71],"to":[72,84],"learn":[73],"how":[74],"signal":[76],"is":[77,93,110],"masked":[78],"by":[79],"acoustic":[81],"noise":[82],"define":[85],"rule.":[90],"However,":[91],"it":[92],"shown":[94],"incorporating":[99],"contextual":[100],"information":[101],"yielded":[102],"better":[103],"even":[106],"when":[107],"no":[108],"denoising":[109],"applied.":[111],"experimental":[113],"analysis":[114],"carried":[115],"out":[116],"on":[117],"Spanish":[119],"SpeechDat-Car":[120],"database":[121],"clear":[123],"improvements":[124],"standard":[126],"VADs":[127],"including":[128],"ITU":[129],"G.729,":[130],"ETSI":[131,134],"AMR":[132],"AFE":[135],"distributed":[137],"recognition":[139],"(DSR),":[140],"other":[142],"recently":[143],"reported":[144],"VADs.":[145],"Index":[146],"Terms:":[147],"voice":[148],"activity":[149],"detection,":[150],"learning,":[154],"enhancement.":[156]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}