{"id":"https://openalex.org/W2004152732","doi":"https://doi.org/10.1109/iscslp.2010.5684488","title":"Using cepstral and prosodic features for Chinese accent identification","display_name":"Using cepstral and prosodic features for Chinese accent identification","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2004152732","doi":"https://doi.org/10.1109/iscslp.2010.5684488","mag":"2004152732"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th 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/A5100721398","display_name":"Jue Hou","orcid":"https://orcid.org/0000-0001-9404-2022"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jue Hou","raw_affiliation_strings":["Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China","Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330628","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-2221-2998"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China","Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China","Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technology Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110111869","display_name":"Jesper \u00d8. Olsen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099903","display_name":"Nokia (China)","ror":"https://ror.org/01607kg94","country_code":"CN","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210099903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jesper Olsen","raw_affiliation_strings":["Nokia Research Center, Beijing, China","Nokia Research Center Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Beijing, China","institution_ids":["https://openalex.org/I4210099903"]},{"raw_affiliation_string":"Nokia Research Center Beijing, China","institution_ids":["https://openalex.org/I4210099903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103093321","display_name":"Jilei Tian","orcid":"https://orcid.org/0000-0002-4588-9398"},"institutions":[{"id":"https://openalex.org/I4210099903","display_name":"Nokia (China)","ror":"https://ror.org/01607kg94","country_code":"CN","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210099903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jilei Tian","raw_affiliation_strings":["Nokia Research Center, Beijing, China","Nokia Research Center Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Beijing, China","institution_ids":["https://openalex.org/I4210099903"]},{"raw_affiliation_string":"Nokia Research Center Beijing, China","institution_ids":["https://openalex.org/I4210099903"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4661,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72619004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9933000206947327,"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":0.9807999730110168,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8091087341308594},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.8035764694213867},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.7692712545394897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7230461835861206},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7054861187934875},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5801882743835449},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5746721625328064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5571138262748718},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5543491244316101},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5257124304771423},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5241111516952515},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.41718918085098267},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.41641396284103394},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41225630044937134},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2483895719051361},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.11147892475128174},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11098283529281616}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8091087341308594},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8035764694213867},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7692712545394897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230461835861206},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7054861187934875},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5801882743835449},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5746721625328064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5571138262748718},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5543491244316101},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5257124304771423},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5241111516952515},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.41718918085098267},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.41641396284103394},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41225630044937134},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2483895719051361},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.11147892475128174},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11098283529281616},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W841901115","https://openalex.org/W1490504384","https://openalex.org/W2107713197","https://openalex.org/W2113419766","https://openalex.org/W2142878924","https://openalex.org/W2146194791","https://openalex.org/W2153635508","https://openalex.org/W2160511961","https://openalex.org/W2160564400","https://openalex.org/W2170348535","https://openalex.org/W2395544453","https://openalex.org/W3120421331","https://openalex.org/W3216401400","https://openalex.org/W6683497447","https://openalex.org/W6712218626"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W4387870978","https://openalex.org/W4298046075","https://openalex.org/W2334135487","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W4207066001"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,98],"propose":[4],"an":[5,36],"approach":[6,116,128],"for":[7],"Chinese":[8,48,120],"accent":[9,121],"identification":[10],"using":[11,141],"both":[12],"cepstral":[13],"and":[14,31,40],"prosodic":[15],"features":[16,30,34,77],"with":[17,82],"gender-dependent":[18,70],"model.":[19],"We":[20,50,68,109],"exploit":[21],"a":[22,130],"combination":[23],"of":[24,38,89,113,140],"conventional":[25,87,138],"Shifted":[26],"Delta":[27],"Cepstrum":[28],"(SDC)":[29],"pitch":[32,57],"contour":[33,58],"as":[35],"example":[37],"segmental":[39],"suprasegmental":[41],"features,":[42],"to":[43,54,62,74,80,105,137],"capture":[44],"the":[45,56,64,76,83,90,100,107,111,114,118],"characteristics":[46],"in":[47,60,78],"accents.":[49,67],"use":[51,99],"cubic":[52],"polynomials":[53],"estimate":[55],"segments":[59],"order":[61,79],"model":[63],"differences":[65],"within":[66],"train":[69],"GMM":[71,91],"acoustic":[72],"models":[73],"express":[75],"deal":[81],"gender":[84],"variation.":[85],"Since":[86],"criterion":[88],"assumption":[92],"cannot":[93],"solve":[94],"those":[95],"multi-feature":[96],"problems,":[97],"support":[101],"vector":[102],"machine":[103],"(SVM)":[104],"make":[106],"decision.":[108],"evaluated":[110],"effectiveness":[112],"proposed":[115],"on":[117],"863":[119],"database.":[122],"The":[123],"result":[124],"shows":[125],"that":[126],"our":[127],"yields":[129],"15.5%":[131],"relative":[132],"error":[133],"rate":[134],"reduction":[135],"compared":[136],"approaches":[139],"only":[142],"SDC":[143],"features.":[144]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}