{"id":"https://openalex.org/W2400323660","doi":"https://doi.org/10.21437/interspeech.2012-651","title":"Prof-life-log: audio environment detection for naturalistic audio streams","display_name":"Prof-life-log: audio environment detection for naturalistic audio streams","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2400323660","doi":"https://doi.org/10.21437/interspeech.2012-651","mag":"2400323660"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-651","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5112244951","display_name":"Ali Ziaei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Ziaei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111469714","display_name":"Abhijeet Sangwan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhijeet Sangwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4861,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86542718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2514","last_page":"2517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/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":0.9921000003814697,"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/computer-science","display_name":"Computer science","score":0.7946450114250183},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6445422172546387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5346478819847107},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.53228360414505},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.46729332208633423},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45785462856292725},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4233851432800293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40381914377212524},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36715394258499146},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12167775630950928},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.088751882314682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946450114250183},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6445422172546387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5346478819847107},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.53228360414505},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.46729332208633423},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45785462856292725},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4233851432800293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40381914377212524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36715394258499146},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12167775630950928},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.088751882314682},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-651","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.5299999713897705},{"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1533561824","https://openalex.org/W2041823554","https://openalex.org/W2094709280","https://openalex.org/W2103861099","https://openalex.org/W2104353650","https://openalex.org/W2114777924","https://openalex.org/W2116652947","https://openalex.org/W2120273544","https://openalex.org/W2130640900","https://openalex.org/W2137197207","https://openalex.org/W2137343183","https://openalex.org/W2154016477","https://openalex.org/W2159277110"],"related_works":["https://openalex.org/W1975321310","https://openalex.org/W1952261593","https://openalex.org/W2014494654","https://openalex.org/W2990323019","https://openalex.org/W3130349901","https://openalex.org/W1579833936","https://openalex.org/W2107361128","https://openalex.org/W2095350775","https://openalex.org/W1578916557","https://openalex.org/W2032826752"],"abstract_inverted_index":{"In":[0,40,53],"this":[1],"study,":[2],"we":[3,107],"develop":[4],"a":[5,21,57,73,139,162],"new":[6],"system":[7,22,130,150],"for":[8,49,85],"real":[9],"world":[10],"audio":[11,18,51,68,133],"environment":[12],"matching.":[13],"Environment":[14],"detection":[15],"within":[16],"unknown":[17,35],"streams":[19],"requires":[20],"that":[23,109,148,157],"operates":[24],"in":[25],"an":[26,78,101,115,152],"unsupervised":[27],"manner":[28],"since":[29],"it":[30,110,137],"will":[31],"be":[32,46],"faced":[33],"with":[34],"environments":[36],"without":[37],"prior":[38],"information.":[39],"addition,":[41],"the":[42,54,89,96,104,125,128],"overall":[43],"solution":[44],"should":[45],"computationally":[47],"efficient":[48],"large":[50,64],"collection.":[52],"proposed":[55,129],"approach,":[56],"Gaussian":[58],"mixture":[59],"model(GMM)":[60],"is":[61,83,92,111,158],"trained":[62],"on":[63,131],"amounts":[65],"of":[66,100,127],"unlabeled":[67],"data":[69],"and":[70,135],"used":[71],"as":[72],"background":[74],"acoustic":[75,79,98,121],"model.":[76],"Subsequently,":[77],"signature":[80],"vector":[81,91],"(ASV)":[82],"computed":[84],"each":[86],"environment.":[87,102],"Here,":[88],"ASV":[90,105],"designed":[93],"to":[94,113,138],"capture":[95],"unique":[97],"characteristics":[99],"Using":[103],"vectors,":[106],"demonstrate":[108,124],"possible":[112],"compute":[114],"effective":[116],"similarity":[117],"measure":[118],"between":[119],"two":[120],"environments.":[122],"We":[123],"performance":[126],"real-world":[132],"data,":[134],"compare":[136],"traditional":[140],"GMM-UBM":[141,164],"(Universal":[142],"Background":[143],"Model)":[144],"system.":[145,165],"Experiments":[146],"show":[147],"our":[149],"achieves":[151],"equal":[153],"error":[154],"rate":[155],"(EER)":[156],"+35%":[159],"better":[160],"than":[161],"baseline":[163]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}