{"id":"https://openalex.org/W136597581","doi":"https://doi.org/10.21437/interspeech.2007-726","title":"Speech-nonspeech discrimination using the information bottleneck method and spectro-temporal modulation index","display_name":"Speech-nonspeech discrimination using the information bottleneck method and spectro-temporal modulation index","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W136597581","doi":"https://doi.org/10.21437/interspeech.2007-726","mag":"136597581"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-726","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5101734352","display_name":"Maria Markaki","orcid":"https://orcid.org/0000-0001-5779-2078"},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Maria Markaki","raw_affiliation_strings":["University of Crete"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Crete","institution_ids":["https://openalex.org/I142617266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079103786","display_name":"Michael Wohlmayr","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088543","display_name":"Institut f\u00fcr Informationsverarbeitung","ror":"https://ror.org/0047j9t38","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210088543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Wohlmayr","raw_affiliation_strings":["Institut f\u00fcr Signalverarbeitung und Sprachkommunikation (4420)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Signalverarbeitung und Sprachkommunikation (4420)","institution_ids":["https://openalex.org/I4210088543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":["University of Crete"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Crete","institution_ids":["https://openalex.org/I142617266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.01395864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2913","last_page":"2916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9970999956130981,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9950000047683716,"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":0.7267273664474487},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7244462966918945},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6730611324310303},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6161561608314514},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.5739437937736511},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.508922815322876},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4676491916179657},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4377012252807617},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4201200008392334},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41839057207107544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41005176305770874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4099518656730652},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13481071591377258},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07029673457145691}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267273664474487},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7244462966918945},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6730611324310303},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6161561608314514},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.5739437937736511},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.508922815322876},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4676491916179657},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4377012252807617},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4201200008392334},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41839057207107544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41005176305770874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4099518656730652},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13481071591377258},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07029673457145691},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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":2,"locations":[{"id":"doi:10.21437/interspeech.2007-726","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.496.5529","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.496.5529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csd.uoc.gr/~mmarkaki/MMILab-MMarkaki_files/is2007_mmarkaki_stylianou.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6700000166893005}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321917","display_name":"General Secretariat for Research and Technology","ror":"https://ror.org/04yeh8h63"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W186298576","https://openalex.org/W1686946872","https://openalex.org/W2013912476","https://openalex.org/W2122516409","https://openalex.org/W2130426352","https://openalex.org/W2142709321","https://openalex.org/W2979454998"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"adopt":[4],"an":[5],"information":[6],"theoretic":[7],"approach-":[8],"the":[9,15,20,48,55,60,70,78,102,123],"Information":[10],"Bottleneck":[11],"method-":[12],"to":[13,54,65,76,118],"extract":[14],"relevant":[16],"spectro-temporal":[17,71],"modulations":[18],"for":[19,43,91,122],"task":[21],"of":[22,47,62,80,111],"speech":[23,93,130],"/":[24],"non-speech":[25,27,95],"dis-crimination-":[26],"events":[28],"include":[29],"music,":[30],"noise":[31],"and":[32,108],"an-imal":[33],"vocalizations.":[34],"A":[35,84],"compact":[36],"representation":[37],"(a":[38],"\u201ccluster":[39],"pro-totype\u201d)":[40],"is":[41,88],"built":[42],"each":[44,66],"class":[45],"consisting":[46],"maximally":[49],"in-formative":[50],"features":[51],"with":[52],"respect":[53],"classification":[56],"task.":[57,125],"We":[58],"assess":[59],"similarity":[61],"a":[63],"sound":[64],"representative":[67],"cluster":[68],"using":[69],"modulation":[72],"index":[73],"(STMI)":[74],"adapted":[75],"handle":[77],"contribution":[79],"different":[81],"frequency":[82],"bands.":[83],"sim-ple":[85],"threshold":[86],"check":[87],"then":[89],"used":[90],"discriminating":[92],"from":[94],"events.":[96],"Conducted":[97],"experiments":[98],"have":[99],"shown":[100],"that":[101],"proposed":[103],"method":[104],"has":[105],"low":[106,114],"complexity":[107],"high":[109],"accuracy":[110],"dis-crimination":[112],"in":[113],"SNR":[115],"conditions":[116],"compared":[117],"recently":[119],"pro-posed":[120],"methods":[121],"same":[124],"Index":[126],"Terms:":[127],"audio":[128],"classification,":[129],"discrimination,":[131],"au-ditory":[132],"model":[133]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
