{"id":"https://openalex.org/W2171449031","doi":"https://doi.org/10.1109/icassp.2011.5947359","title":"Speaker characterization using spectral subband energy ratio based on Harmonic plus Noise Model","display_name":"Speaker characterization using spectral subband energy ratio based on Harmonic plus Noise Model","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2171449031","doi":"https://doi.org/10.1109/icassp.2011.5947359","mag":"2171449031"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanhua Long","raw_affiliation_strings":["IFLY Speech Laboratory, University of Science and Technology, China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IFLY Speech Laboratory, University of Science and Technology, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061850214","display_name":"Zhijie Yan","orcid":"https://orcid.org/0000-0001-8065-0748"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-Jie Yan","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["IFLY Speech Laboratory, University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"IFLY Speech Laboratory, University of Science and Technology, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["IFLY Speech Laboratory, University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"IFLY Speech Laboratory, University of Science and Technology, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056415893"],"corresponding_institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.8552,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81035552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"101","issue":null,"first_page":"4520","last_page":"4523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9940999746322632,"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/speech-recognition","display_name":"Speech recognition","score":0.7096157073974609},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6350712776184082},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.5892778635025024},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5805313587188721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5689023733139038},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5546351075172424},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.5363368391990662},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5138009190559387},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5007436275482178},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.49737241864204407},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44609972834587097},{"id":"https://openalex.org/keywords/harmonic-analysis","display_name":"Harmonic analysis","score":0.4437176585197449},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4134103059768677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2694851756095886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25739049911499023},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.14998164772987366},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14510729908943176},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13798567652702332},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07057163119316101},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06172877550125122}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7096157073974609},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6350712776184082},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.5892778635025024},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5805313587188721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5689023733139038},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5546351075172424},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.5363368391990662},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5138009190559387},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5007436275482178},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.49737241864204407},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44609972834587097},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.4437176585197449},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4134103059768677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2694851756095886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25739049911499023},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.14998164772987366},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14510729908943176},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13798567652702332},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07057163119316101},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06172877550125122},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W6725010","https://openalex.org/W95551363","https://openalex.org/W1760200923","https://openalex.org/W2041823554","https://openalex.org/W2070176749","https://openalex.org/W2084562624","https://openalex.org/W2088632109","https://openalex.org/W2100643000","https://openalex.org/W2128391065","https://openalex.org/W2129082420","https://openalex.org/W2165376938","https://openalex.org/W6603921752","https://openalex.org/W6667507107"],"related_works":["https://openalex.org/W3162157266","https://openalex.org/W2162084437","https://openalex.org/W2102353451","https://openalex.org/W3044927199","https://openalex.org/W1579696083","https://openalex.org/W2026048727","https://openalex.org/W2525517395","https://openalex.org/W4206226528","https://openalex.org/W94697941","https://openalex.org/W2131300395"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,105],"feature":[4],"extraction":[5],"for":[6,26,39,96],"speaker":[7,75,97,100],"characterization":[8],"by":[9,121,123],"exploring":[10],"the":[11,14,19,27,30,33,40,43,52,59,67,74,83,87,110,113,117,126],"relationship":[12],"between":[13],"two":[15],"distinct":[16],"components":[17],"of":[18,29,42,51,86,93,112],"speech":[20,53],"signal,":[21],"one":[22],"is":[23,35],"harmonics":[24],"accounting":[25,38],"periodicity":[28],"signal":[31,54],"and":[32,48,90],"other":[34],"modulated":[36],"noise":[37,49],"turbulences":[41],"glottal":[44,91],"airflow.":[45],"The":[46,99],"harmonic":[47],"parts":[50],"are":[55,79],"decomposed":[56],"based":[57,103],"on":[58,104],"Harmonic":[60],"plus":[61],"Noise":[62],"Model":[63],"approach.":[64],"We":[65],"estimate":[66],"spectral":[68],"subband":[69],"energy":[70],"ratios":[71],"(SSERs)":[72],"as":[73],"characteristic":[76],"features,":[77,115],"which":[78],"expected":[80],"to":[81],"reflect":[82],"interaction":[84],"property":[85],"vocal":[88],"tract":[89],"airflow":[92],"individual":[94],"speakers":[95],"verification.":[98],"verification":[101],"experiments":[102],"GMM-UBM":[106],"system":[107],"have":[108],"shown":[109],"efficiency":[111],"SSER":[114],"reducing":[116],"error":[118],"equal":[119],"rate":[120],"27.2%":[122],"combining":[124],"with":[125],"conventional":[127],"MFCC":[128],"features.":[129]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}