{"id":"https://openalex.org/W2517628875","doi":"https://doi.org/10.21437/interspeech.2016-175","title":"Hierarchical Classification of Speaker and Background Noise and Estimation of SNR Using Sparse Representation","display_name":"Hierarchical Classification of Speaker and Background Noise and Estimation of SNR Using Sparse Representation","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2517628875","doi":"https://doi.org/10.21437/interspeech.2016-175","mag":"2517628875"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-175","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","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/A5103008705","display_name":"K V Vijay Girish","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K.V. Vijay Girish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069802599","display_name":"A. G. Ramakrishnan","orcid":"https://orcid.org/0000-0002-3646-1955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A.G. Ramakrishnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111836918","display_name":"T. Ananthapadmanabha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T.V. Ananthapadmanabha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0994,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77550222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2972","last_page":"2976"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9926000237464905,"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":0.9502999782562256,"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":0.7866644859313965},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6934879422187805},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6882116794586182},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6543923616409302},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5508195161819458},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.5364065766334534},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5300490856170654},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5102081298828125},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5064915418624878},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4896877110004425},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48153358697891235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4385250210762024},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4164403975009918},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.25430727005004883},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13266414403915405},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09360146522521973},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06634238362312317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7866644859313965},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6934879422187805},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6882116794586182},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6543923616409302},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5508195161819458},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.5364065766334534},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5300490856170654},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5102081298828125},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5064915418624878},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4896877110004425},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48153358697891235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4385250210762024},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4164403975009918},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25430727005004883},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13266414403915405},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09360146522521973},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06634238362312317},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2016-175","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"In":[0,34],"the":[1,9,17,27,44,54,57,69,75,93,124,134,140,146,149,175],"analysis":[2,42],"of":[3,5,8,19,25,31,43,56,74,95,130,136,148,197],"recordings":[4],"conversations,":[6],"one":[7,73],"motivations":[10],"is":[11,47,65,71,116,126,179],"to":[12,15,39,50,66,91,173],"be":[13],"able":[14],"identify":[16,67,174],"nature":[18],"background":[20,186],"noise":[21,37,107,114,142,153,158],"as":[22],"a":[23,32,35,96,110,113,163,195],"means":[24],"identifying":[26],"possible":[28],"geographical":[29],"location":[30],"speaker.":[33],"high":[36],"environment,":[38],"minimize":[40],"manual":[41],"recording,":[45,58,99],"it":[46],"also":[48],"desirable":[49],"automatically":[51],"locate":[52],"only":[53],"segments":[55],"which":[59],"contain":[60],"speech.":[61],"The":[62,167],"next":[63],"task":[64],"if":[68],"speech":[70,98,156,178],"from":[72,133],"known":[76],"people.":[77],"A":[78],"dictionary":[79],"learning":[80],"and":[81,122,139,152,157,188],"block":[82,119],"sparsity":[83,120],"based":[84],"source":[85,143,164],"recovery":[86,165],"approach":[87],"has":[88],"been":[89],"used":[90,172],"estimate":[92],"SNR":[94,196],"noisy":[97],"simulated":[100],"at":[101,194],"different":[102,106],"SNRs":[103],"using":[104,118,128,162],"ten":[105],"sources.":[108],"Given":[109],"test":[111],"utterance,":[112],"label":[115],"assigned":[117],"approach,":[121],"subsequently,":[123],"speaker":[125,137,151,192],"classified":[127],"sum":[129],"weights":[131],"recovered":[132],"concatenation":[135],"dictionaries":[138,147],"identified":[141,150],"dictionary.":[144],"Using":[145],"sources,":[154],"framewise":[155],"energy":[159,168],"are":[160,170],"estimated":[161],"method.":[166],"estimates":[169],"then":[171],"segments,":[176],"where":[177],"present.":[180],"We":[181],"obtain":[182],"100%":[183],"accuracy":[184],"for":[185,191],"classification":[187,193],"around":[189],"90%":[190],"10":[198],"dB.":[199]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}