{"id":"https://openalex.org/W2032429609","doi":"https://doi.org/10.1109/icassp.2014.6854527","title":"Mandarin tone classification without pitch tracking","display_name":"Mandarin tone classification without pitch tracking","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2032429609","doi":"https://doi.org/10.1109/icassp.2014.6854527","mag":"2032429609"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5088320958","display_name":"Neville Ryant","orcid":"https://orcid.org/0000-0003-2545-6912"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neville Ryant","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania","Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]},{"raw_affiliation_string":"Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043406907","display_name":"Jiahong Yuan","orcid":"https://orcid.org/0009-0008-2162-7167"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiahong Yuan","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania","Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]},{"raw_affiliation_string":"Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055868875","display_name":"Mark Liberman","orcid":"https://orcid.org/0000-0002-8605-9024"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Liberman","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania","Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]},{"raw_affiliation_string":"Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.064,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.87259547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4868","last_page":"4872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7865937948226929},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6870565414428711},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6094805598258972},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.6092519760131836},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5694666504859924},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5638611316680908},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.555465579032898},{"id":"https://openalex.org/keywords/amplitude","display_name":"Amplitude","score":0.5055630207061768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49756601452827454},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4502708613872528},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38318002223968506},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08618292212486267},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07322797179222107}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7865937948226929},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6870565414428711},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6094805598258972},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.6092519760131836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5694666504859924},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5638611316680908},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.555465579032898},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.5055630207061768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49756601452827454},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4502708613872528},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38318002223968506},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08618292212486267},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07322797179222107},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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":2,"locations":[{"id":"doi:10.1109/icassp.2014.6854527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.651.1710","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.651.1710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://languagelog.ldc.upenn.edu/myl/ToneWithoutPitch.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W50577135","https://openalex.org/W103244930","https://openalex.org/W108550785","https://openalex.org/W1593404165","https://openalex.org/W1648698152","https://openalex.org/W1665214252","https://openalex.org/W1709739193","https://openalex.org/W1904365287","https://openalex.org/W1966512026","https://openalex.org/W1997854624","https://openalex.org/W2052436446","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2155820021","https://openalex.org/W2160212752","https://openalex.org/W2163426739","https://openalex.org/W2166697034","https://openalex.org/W2353525634","https://openalex.org/W2401167848","https://openalex.org/W2406467606","https://openalex.org/W2990347461","https://openalex.org/W3211740065","https://openalex.org/W6604322312","https://openalex.org/W6637086781","https://openalex.org/W6637242042","https://openalex.org/W6803881137"],"related_works":["https://openalex.org/W2393887907","https://openalex.org/W2347443630","https://openalex.org/W2388826840","https://openalex.org/W2481138693","https://openalex.org/W2379831327","https://openalex.org/W2386691339","https://openalex.org/W156219719","https://openalex.org/W2365805939","https://openalex.org/W2287147624","https://openalex.org/W2163874654"],"abstract_inverted_index":{"A":[0],"deep":[1],"neural":[2],"network":[3],"(DNN)":[4],"based":[5,29],"classifier":[6],"achieved":[7,83],"27.38%":[8],"frame":[9],"error":[10,16],"rate":[11,17],"(FER)":[12],"and":[13,44,51,57,75,91,103],"15.62%":[14],"segment":[15],"(SER)":[18],"in":[19,24,84],"recognizing":[20],"five":[21],"tonal":[22],"categories":[23],"Mandarin":[25],"Chinese":[26],"broadcast":[27],"news,":[28],"on":[30,70],"40":[31],"mel-frequency":[32],"cepstral":[33],"coefficients":[34],"(MFCCs).":[35],"The":[36],"same":[37],"architecture":[38],"scored":[39],"substantially":[40,63],"lower":[41],"when":[42],"trained":[43],"tested":[45],"with":[46],"F":[47,99],"<sub":[48,100],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[49,101],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</sub>":[50,102],"amplitude":[52,104],"parameters":[53],"alone:":[54],"40.05%":[55],"FER":[56],"22.66%":[58],"SER.":[59],"These":[60],"results":[61,69],"are":[62,76],"better":[64,78],"than":[65,79],"the":[66,97],"best":[67],"previously-reported":[68],"broadcast-news":[71],"tone":[72],"classification":[73],"[1]":[74],"also":[77],"a":[80],"human":[81],"listener":[82],"categorizing":[85],"test":[86],"stimuli":[87],"created":[88],"by":[89],"amplitude-":[90],"frequency-modulating":[92],"complex":[93],"tones":[94],"to":[95],"match":[96],"extracted":[98],"parameters.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}