{"id":"https://openalex.org/W3163724562","doi":"https://doi.org/10.1109/icassp39728.2021.9413838","title":"Speaking Rate and Tonal Realization in Mandarin Chinese: What Can We Learn From Large Speech Corpora?","display_name":"Speaking Rate and Tonal Realization in Mandarin Chinese: What Can We Learn From Large Speech Corpora?","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163724562","doi":"https://doi.org/10.1109/icassp39728.2021.9413838","mag":"3163724562"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5043406907","display_name":"Jiahong Yuan","orcid":"https://orcid.org/0009-0008-2162-7167"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiahong Yuan","raw_affiliation_strings":["Baidu Research, USA"],"affiliations":[{"raw_affiliation_string":"Baidu Research, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016543371","display_name":"Kenneth Church","orcid":"https://orcid.org/0000-0001-8378-6069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenneth Church","raw_affiliation_strings":["Baidu Research, USA"],"affiliations":[{"raw_affiliation_string":"Baidu Research, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043406907"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1753,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52666355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6463","last_page":"6467"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":1.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9943000078201294,"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.9188953638076782},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.9123110175132751},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.8363245725631714},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.810991644859314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6876119375228882},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5600364804267883},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.49231064319610596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4484894871711731},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30795323848724365},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23879730701446533},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0878106951713562},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.058898359537124634}],"concepts":[{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.9188953638076782},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.9123110175132751},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.8363245725631714},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.810991644859314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6876119375228882},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5600364804267883},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.49231064319610596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4484894871711731},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30795323848724365},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23879730701446533},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0878106951713562},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.058898359537124634},{"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/icassp39728.2021.9413838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W49568767","https://openalex.org/W137920126","https://openalex.org/W1506507878","https://openalex.org/W1801810991","https://openalex.org/W1986639080","https://openalex.org/W1989235927","https://openalex.org/W2019528670","https://openalex.org/W2038784064","https://openalex.org/W2093961534","https://openalex.org/W2110332474","https://openalex.org/W2589745698","https://openalex.org/W2613728820","https://openalex.org/W2749455670","https://openalex.org/W2988331831","https://openalex.org/W4230684940","https://openalex.org/W4242195657","https://openalex.org/W4390912579","https://openalex.org/W4390926499","https://openalex.org/W6601972353","https://openalex.org/W6813089768","https://openalex.org/W6860861070"],"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/W2163874654","https://openalex.org/W2365805939","https://openalex.org/W2287147624","https://openalex.org/W156219719"],"abstract_inverted_index":{"Two":[0],"Mandarin":[1],"speech":[2,24],"corpora":[3],"were":[4],"used":[5],"to":[6,48,147,151],"investigate":[7],"tonal":[8,178],"realization":[9,57,153],"in":[10,38,60,130,177],"terms":[11],"of":[12,19,23,52,58,96,103,118,132,136,154],"duration":[13],"and":[14,76,87,115,121,170],"pitch.":[15],"The":[16,30],"data":[17],"consist":[18],"nearly":[20],"1000":[21],"hours":[22],"from":[25,145],"more":[26,78],"than":[27],"1600":[28],"speakers.":[29],"two":[31,66],"corpora,":[32,134],"both":[33,135,168],"developed":[34],"for":[35,68,80],"ASR,":[36],"differ":[37],"speaking":[39,53,70,160],"rate":[40,54,161],"by":[41],"approximately":[42],"25%.":[43],"This":[44],"provides":[45],"an":[46,174],"opportunity":[47],"examine":[49],"the":[50,56,93,106,110,116,127,133,152,155,159],"influence":[51],"on":[55,92,126],"tones":[59,75],"natural":[61],"speech.":[62],"Our":[63,164],"analysis":[64],"found":[65,142],"differences":[67],"slower":[69],"rates:":[71],"(1)":[72],"lower":[73,91],"\"static\"":[74],"(2)":[77],"change":[79],"\"dynamic\"":[81,156],"tones.":[82],"Tone":[83,88,119,122],"1":[84],"was":[85,90,113,124],"higher":[86,125],"3":[89],"first":[94],"syllable":[95,112,129],"disyllabic":[97],"words,":[98],"suggesting":[99],"a":[100,143],"metrical":[101,171],"structure":[102,172],"left-prominence.":[104],"On":[105],"other":[107],"hand,":[108],"however,":[109],"second":[111,128],"longer,":[114],"slope":[117],"2":[120],"4":[123],"one":[131],"which":[137],"suggest":[138],"right-prominence.":[139],"We":[140],"also":[141],"shift":[144],"right-prominence":[146],"left-prominence,":[148],"with":[149],"respect":[150],"tones,":[157],"when":[158],"became":[162],"slower.":[163],"study":[165],"demonstrated":[166],"that":[167],"phrasing":[169],"play":[173],"important":[175],"role":[176],"realization.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
