{"id":"https://openalex.org/W3082120808","doi":"https://doi.org/10.1109/spcom50965.2020.9179491","title":"Classification of Speech vs. Speech with Background Music","display_name":"Classification of Speech vs. Speech with Background Music","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3082120808","doi":"https://doi.org/10.1109/spcom50965.2020.9179491","mag":"3082120808"},"language":"en","primary_location":{"id":"doi:10.1109/spcom50965.2020.9179491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","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/A5006151531","display_name":"Mrinmoy Bhattacharjee","orcid":"https://orcid.org/0000-0002-5348-9378"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Mrinmoy Bhattacharjee","raw_affiliation_strings":["Dept. of EEE, IIT Guwahati, Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Dept. of EEE, IIT Guwahati, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052129812","display_name":"S. R. Mahadeva Prasanna","orcid":"https://orcid.org/0000-0002-8135-7938"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]},{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S.R. Mahadeva Prasanna","raw_affiliation_strings":["Dept. of EEE, IIT Guwahati, Dharwad, India"],"affiliations":[{"raw_affiliation_string":"Dept. of EEE, IIT Guwahati, Dharwad, India","institution_ids":["https://openalex.org/I4210152718","https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041308578","display_name":"Prithwijit Guha","orcid":"https://orcid.org/0000-0003-2885-0026"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prithwijit Guha","raw_affiliation_strings":["Dept. of EEE, IIT Guwahati, Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Dept. of EEE, IIT Guwahati, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006151531"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.1515,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.43298223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11309","display_name":"Music 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":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8672720193862915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7594335079193115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7275100350379944},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6786226034164429},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5722909569740295},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5136458277702332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5135693550109863},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5063766241073608},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.481611430644989},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.4576219320297241},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4272758364677429},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4224604368209839}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8672720193862915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7594335079193115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7275100350379944},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6786226034164429},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5722909569740295},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5136458277702332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5135693550109863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5063766241073608},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.481611430644989},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.4576219320297241},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4272758364677429},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4224604368209839},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom50965.2020.9179491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W146976060","https://openalex.org/W1505126044","https://openalex.org/W1790748249","https://openalex.org/W2000911789","https://openalex.org/W2031339194","https://openalex.org/W2040378088","https://openalex.org/W2099988055","https://openalex.org/W2107789863","https://openalex.org/W2120642371","https://openalex.org/W2127566601","https://openalex.org/W2128838222","https://openalex.org/W2133824856","https://openalex.org/W2142838865","https://openalex.org/W2144345993","https://openalex.org/W2147437692","https://openalex.org/W2150415460","https://openalex.org/W2221409856","https://openalex.org/W2300296386","https://openalex.org/W2530921900","https://openalex.org/W2552071709","https://openalex.org/W2607177476","https://openalex.org/W2766167392","https://openalex.org/W2783566019","https://openalex.org/W3124794156","https://openalex.org/W6606052675","https://openalex.org/W6676071220"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W1840351222","https://openalex.org/W4225315139","https://openalex.org/W4385881881"],"abstract_inverted_index":{"Applications":[0],"that":[1,14,33,95],"perform":[2],"enhancement":[3],"of":[4,64,68,92,109],"speech":[5,29,51,76],"containing":[6],"background":[7,31],"music":[8,32,53,78],"require":[9],"a":[10,24,83,106,123,134],"critical":[11],"preprocessing":[12,25],"step":[13],"can":[15],"efficiently":[16],"detect":[17,28],"such":[18,23],"segments.":[19],"This":[20,80],"work":[21,81],"proposes":[22,82],"method":[26],"to":[27,73,86,98],"with":[30,154],"is":[34,43,105,120,131],"mixed":[35],"at":[36],"different":[37],"SNR":[38],"levels.":[39],"A":[40],"bag-of-words":[41],"approach":[42,130],"proposed":[44,103,129,144],"in":[45,152],"this":[46],"work.":[47],"Representative":[48],"dictionaries":[49],"from":[50,114],"and":[52,77,136,151],"data":[54],"are":[55,60,71],"first":[56],"learned.":[57],"The":[58,102,118,128,143],"signals":[59],"processed":[61],"as":[62],"spectrograms":[63,70],"1s":[65,110],"intervals.":[66],"Rows":[67],"these":[69],"used":[72],"learn":[74],"separate":[75],"dictionaries.":[79,117],"weighting":[84],"scheme":[85],"reduce":[87],"confusion":[88],"by":[89],"suppressing":[90],"codewords":[91],"one":[93],"class":[94],"have":[96],"similarities":[97],"the":[99,115,155],"other":[100],"class.":[101],"feature":[104,145],"weighted":[107],"histogram":[108],"audio":[111],"intervals":[112],"obtained":[113],"learned":[116],"classification":[119],"performed":[121],"using":[122],"deep":[124],"neural":[125],"network":[126],"classifier.":[127],"validated":[132],"against":[133],"baseline":[135],"benchmarked":[137],"over":[138],"two":[139],"publicly":[140],"available":[141],"datasets.":[142],"shows":[146],"promising":[147],"results,":[148],"both":[149],"individually":[150],"combination":[153],"baseline.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}