{"id":"https://openalex.org/W266841485","doi":"https://doi.org/10.21437/interspeech.2004-346","title":"An adaptive band-partitioning spectral entropy based speech detection in realistic noisy environments","display_name":"An adaptive band-partitioning spectral entropy based speech detection in realistic noisy environments","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W266841485","doi":"https://doi.org/10.21437/interspeech.2004-346","mag":"266841485"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-346","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-346","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/A5033706944","display_name":"Kun-Ching Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kun-Ching Wang","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5033706944"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.02998598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"957","last_page":"960"},"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":0.9980999827384949,"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":0.9955999851226807,"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/spectrogram","display_name":"Spectrogram","score":0.8365965485572815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6863710880279541},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6551505327224731},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.595592737197876},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5429941415786743},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5316689014434814},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49648529291152954},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47095900774002075},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.46013444662094116},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.44384241104125977},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.420302152633667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4197343587875366},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4178745150566101},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3755452036857605},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2787575423717499},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06107550859451294}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8365965485572815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6863710880279541},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6551505327224731},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.595592737197876},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5429941415786743},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5316689014434814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49648529291152954},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47095900774002075},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.46013444662094116},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.44384241104125977},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.420302152633667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4197343587875366},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4178745150566101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3755452036857605},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2787575423717499},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06107550859451294},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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:10.21437/interspeech.2004-346","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-346","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W15516501","https://openalex.org/W182487737","https://openalex.org/W1917666251","https://openalex.org/W1995875735","https://openalex.org/W2069501481","https://openalex.org/W2090499995","https://openalex.org/W2104132386","https://openalex.org/W2108289863","https://openalex.org/W2150125142","https://openalex.org/W2171271801","https://openalex.org/W2535438430"],"related_works":["https://openalex.org/W1976952689","https://openalex.org/W1975881626","https://openalex.org/W1572861854","https://openalex.org/W4252208810","https://openalex.org/W2341426843","https://openalex.org/W2539491809","https://openalex.org/W1984921740","https://openalex.org/W2070982348","https://openalex.org/W2559040841","https://openalex.org/W1968776176"],"abstract_inverted_index":{"Generally,":[0],"the":[1,12,27,47,69,72,106,123,141],"feature":[2,39,56],"parameters":[3],"used":[4],"for":[5,129],"speech":[6,17,31,51,60,93,100],"detection":[7,18,94],"are":[8,80],"highly":[9],"sensitive":[10],"to":[11,57,98,111,133],"environment.":[13],"The":[14],"performance":[15],"of":[16,29,50,75,78],"is":[19,96,109,126,149],"severely":[20],"degraded":[21],"under":[22],"realistic":[23],"noisy":[24],"environments":[25],"since":[26],"characteristics":[28],"a":[30,42,54,59,62,152],"signal":[32],"cannot":[33],"be":[34],"fully":[35],"expressed":[36],"by":[37],"those":[38],"parameters.":[40],"As":[41],"result,":[43],"this":[44],"study":[45],"seeks":[46],"acoustic":[48],"fingerprints":[49],"spectrogram":[52],"as":[53],"robust":[55],"distinguish":[58],"from":[61],"non-speech,":[63],"especially":[64],"in":[65,102,113,151],"adverse":[66,103],"environments,":[67],"and":[68,136,148],"fact":[70],"that":[71,122],"frequency":[73,84],"energies":[74],"difference":[76],"types":[77],"noise":[79,138],"concentrated":[81],"on":[82],"different":[83],"bands":[85],"[12],":[86],"an":[87],"ABSE":[88,124],"(Adaptive":[89],"Band-partitioning":[90],"Spectral":[91],"Entropy)-based":[92],"algorithm":[95,108,144],"proposed":[97,142],"detect":[99],"signals":[101],"environments.":[104],"Additionally,":[105],"ABSE-based":[107,143],"demonstrated":[110],"work":[112],"real-time":[114],"with":[115],"minimal":[116],"processing":[117],"delay.":[118],"Experimental":[119],"results":[120],"indicate":[121],"parameter":[125],"very":[127],"effective":[128],"several":[130],"SNRs":[131],"(Signal":[132],"Noise":[134],"Ratios)":[135],"various":[137],"conditions.":[139],"Furthermore,":[140],"outperforms":[145],"other":[146],"approaches":[147],"reliable":[150],"real":[153],"car.":[154]},"counts_by_year":[{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}