{"id":"https://openalex.org/W2991178841","doi":"https://doi.org/10.1109/sped.2019.8906597","title":"Background Sound Classification in Speech Audio Segments","display_name":"Background Sound Classification in Speech Audio Segments","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2991178841","doi":"https://doi.org/10.1109/sped.2019.8906597","mag":"2991178841"},"language":"en","primary_location":{"id":"doi:10.1109/sped.2019.8906597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2019.8906597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5112584258","display_name":"Janvijay Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Janvijay Singh","raw_affiliation_strings":["Indian Institute of Technology (BHU) Varanasi,Varanasi,India","Indian Institute of Technology (BHU) Varanasi, Varanasi, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology (BHU) Varanasi,Varanasi,India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]},{"raw_affiliation_string":"Indian Institute of Technology (BHU) Varanasi, Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009725385","display_name":"Raviraj Joshi","orcid":"https://orcid.org/0000-0003-1892-1812"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raviraj Joshi","raw_affiliation_strings":["Indian Institute of Technology Madras,Chennai,India","Indian Institute of Technology Madras, Chennai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras,Chennai,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Indian Institute of Technology Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112584258"],"corresponding_institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"],"apc_list":null,"apc_paid":null,"fwci":0.9951,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.77102001,"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8128209114074707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6555582284927368},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5720252990722656},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5398086905479431},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5211932063102722},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5112564563751221},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4896679222583771},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.48095813393592834},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4584372639656067},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42498475313186646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4107773005962372},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3756588399410248},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3555578589439392}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8128209114074707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6555582284927368},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5720252990722656},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5398086905479431},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5211932063102722},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5112564563751221},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4896679222583771},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.48095813393592834},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4584372639656067},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42498475313186646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4107773005962372},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3756588399410248},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3555578589439392},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped.2019.8906597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2019.8906597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.8299999833106995,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1560724230","https://openalex.org/W1686810756","https://openalex.org/W2038484192","https://openalex.org/W2041127133","https://openalex.org/W2052666245","https://openalex.org/W2130640900","https://openalex.org/W2135342008","https://openalex.org/W2137343183","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2509065397","https://openalex.org/W2526050071","https://openalex.org/W2566935005","https://openalex.org/W2593116425","https://openalex.org/W2593451766","https://openalex.org/W2676925568","https://openalex.org/W2885392124","https://openalex.org/W2962910554","https://openalex.org/W3098357269","https://openalex.org/W6603838645","https://openalex.org/W6637373629","https://openalex.org/W6754161993"],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W2157598242","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W2620660273","https://openalex.org/W4243125559","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Background":[0],"sound":[1,9,98,121],"classification":[2,40,58,83,95,144,160],"is":[3,17],"the":[4,12,31,74,82,94,159],"task":[5],"of":[6,33,36,63,84,96,145],"identifying":[7],"secondary":[8],"sources":[10],"in":[11,29,99,147],"surrounding":[13],"environment.":[14],"Real-time":[15],"speech":[16,46],"always":[18],"accompanied":[19],"by":[20],"a":[21,34,107,118,130,139],"context.":[22],"This":[23],"context":[24,146],"can":[25],"be":[26],"very":[27],"helpful":[28],"enhancing":[30],"behavior":[32],"variety":[35],"applications.":[37],"Traditionally,":[38],"audio":[39,100],"tasks":[41],"have":[42,54,71,78],"mainly":[43],"focused":[44,80],"on":[45,81],"due":[47],"to":[48,157],"its":[49],"wide":[50],"applicability.":[51],"Recent":[52],"works":[53,77],"explored":[55],"environmental":[56],"scene":[57],"using":[59,111,138],"acoustic":[60,87,149],"features.":[61],"Availability":[62],"different":[64],"datasets":[65],"like":[66,141],"UrbanSound,":[67],"ESC50,":[68],"and":[69,122],"AUDIOSET":[70],"further":[72],"aided":[73],"process.":[75],"Previous":[76],"mostly":[79],"independently":[85],"occurring":[86],"events.":[88],"In":[89],"this":[90],"work,":[91],"we":[92],"explore":[93],"background":[97,120],"recordings":[101],"containing":[102],"human":[103,126],"speech.":[104],"We":[105,128],"prepare":[106],"new":[108],"dataset":[109],"YBSS-200":[110],"youtube":[112],"videos":[113],"where":[114],"each":[115],"sample":[116],"contains":[117],"distinct":[119],"an":[123],"accompanying":[124],"foreground":[125],"voice.":[127],"present":[129],"convolutional":[131],"neural":[132],"network":[133],"based":[134],"transfer":[135],"learning":[136],"approach":[137],"VGG":[140],"Network":[142],"for":[143],"such":[148],"signals.":[150],"Specific":[151],"data":[152],"augmentation":[153],"techniques":[154],"were":[155],"used":[156],"improve":[158],"results.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}