{"id":"https://openalex.org/W2044522061","doi":"https://doi.org/10.1109/iscslp.2014.6936706","title":"Psychoacoustic model compensation with robust feature set for speaker verification in additive noise","display_name":"Psychoacoustic model compensation with robust feature set for speaker verification in additive noise","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2044522061","doi":"https://doi.org/10.1109/iscslp.2014.6936706","mag":"2044522061"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","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/A5103959037","display_name":"Ashish Panda","orcid":null},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"Ashish Panda","raw_affiliation_strings":["TCS Innovation Lab, Mumbai, India","TCS Innovation Lab, Mumbai, Yantra Park, Thane, 400601, India"],"affiliations":[{"raw_affiliation_string":"TCS Innovation Lab, Mumbai, India","institution_ids":["https://openalex.org/I55215948"]},{"raw_affiliation_string":"TCS Innovation Lab, Mumbai, Yantra Park, Thane, 400601, India","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103959037"],"corresponding_institution_ids":["https://openalex.org/I136199984","https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":1.1646,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7883803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"629","last_page":"632"},"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":0.9998000264167786,"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":0.9987000226974487,"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":0.7633442878723145},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.7321269512176514},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7316757440567017},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6957790851593018},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6719746589660645},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6070979833602905},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.546213686466217},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.497852087020874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4579237401485443},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.45172637701034546},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.44782957434654236},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.28013917803764343},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.220237135887146},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.13541072607040405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633442878723145},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.7321269512176514},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7316757440567017},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6957790851593018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6719746589660645},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6070979833602905},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.546213686466217},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.497852087020874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4579237401485443},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.45172637701034546},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.44782957434654236},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28013917803764343},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.220237135887146},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.13541072607040405},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2041823554","https://openalex.org/W2045607566","https://openalex.org/W2069976350","https://openalex.org/W2085083351","https://openalex.org/W2090716422","https://openalex.org/W2097464745","https://openalex.org/W2121061347","https://openalex.org/W2129066450","https://openalex.org/W2137075158","https://openalex.org/W2150769028","https://openalex.org/W2157685287","https://openalex.org/W6683218471"],"related_works":["https://openalex.org/W2048014685","https://openalex.org/W2370972896","https://openalex.org/W2986378528","https://openalex.org/W3178345791","https://openalex.org/W2092661960","https://openalex.org/W1550854977","https://openalex.org/W4231055618","https://openalex.org/W2949211747","https://openalex.org/W3005742472","https://openalex.org/W2588855097"],"abstract_inverted_index":{"This":[0,44],"paper":[1],"addresses":[2],"the":[3,9,47,69,79,115,127],"problem":[4],"of":[5,11,49,90],"speaker":[6,35],"verification":[7,36],"in":[8,85],"presence":[10],"additive":[12,86],"noise":[13,27,122],"for":[14,82,108],"resource":[15,109],"deficient":[16,110],"languages.":[17,111],"Psychoacoustic":[18],"model":[19,74],"compensation":[20,81],"(Psy-Comp)":[21],"has":[22],"been":[23],"shown":[24],"to":[25,29,51],"impart":[26],"robustness":[28],"Gaussian":[30],"Mixture":[31],"Model":[32],"(GMM)":[33],"based":[34],"systems":[37],"using":[38],"Mel":[39],"Frequency":[40],"Cepstral":[41,60],"Coefficients":[42],"(MFCCs).":[43],"work":[45],"extends":[46],"idea":[48],"Psy-Comp":[50],"incorporate":[52],"a":[53,73],"more":[54],"robust":[55],"feature":[56],"set,":[57],"which":[58],"includes":[59],"Mean":[61],"Subtraction":[62],"(CMS)":[63],"and":[64,102],"\u0394":[65],"coefficients":[66],"along":[67],"with":[68,114,119,126],"MFCCs.":[70],"We":[71],"propose":[72],"domain":[75],"CMS":[76],"operation":[77],"following":[78],"psychoacoustic":[80],"improved":[83,124],"performance":[84,125],"noise.":[87],"An":[88],"advantage":[89],"this":[91],"approach":[92],"is":[93],"that":[94],"it":[95,104],"does":[96],"not":[97],"require":[98],"specialized":[99],"developmental":[100],"data":[101],"hence":[103],"may":[105],"be":[106],"suitable":[107],"Experiments":[112],"conducted":[113],"NIST-2000":[116],"database":[117],"corrupted":[118],"real-life":[120],"street":[121],"show":[123],"proposed":[128],"method.":[129]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}