{"id":"https://openalex.org/W2045150372","doi":"https://doi.org/10.1109/icassp.2010.5495128","title":"Using duration and pitch for mandarin digit string recognition","display_name":"Using duration and pitch for mandarin digit string recognition","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2045150372","doi":"https://doi.org/10.1109/icassp.2010.5495128","mag":"2045150372"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal 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/A5103264680","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-3200-1513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Toshiba (China) Research and Development Center, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba (China) Research and Development Center, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109488356","display_name":"Yusuke Kida","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Kida","raw_affiliation_strings":["Corporate Research & Development Center, Toshiba Corporation, Japan","[Corporate Research and Development Center, Toshiba Corporation, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Corporate Research & Development Center, Toshiba Corporation, Japan","institution_ids":["https://openalex.org/I1292669757"]},{"raw_affiliation_string":"[Corporate Research and Development Center, Toshiba Corporation, Japan]","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101475514","display_name":"Xiang Yan","orcid":"https://orcid.org/0000-0002-5309-9898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yan","raw_affiliation_strings":["Toshiba (China) Research and Development Center, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba (China) Research and Development Center, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035476293","display_name":"Ding Pei","orcid":"https://orcid.org/0000-0002-3995-0690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei Ding","raw_affiliation_strings":["Toshiba (China) Research and Development Center, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba (China) Research and Development Center, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061724331","display_name":"Lei He","orcid":"https://orcid.org/0000-0003-3028-6305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Toshiba (China) Research and Development Center, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba (China) Research and Development Center, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11178044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"4846","last_page":"4849"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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":0.9984999895095825,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8575938940048218},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.8013383150100708},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7903551459312439},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7132169008255005},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6220210790634155},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5854747295379639},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5480945706367493},{"id":"https://openalex.org/keywords/numerical-digit","display_name":"Numerical digit","score":0.5262888073921204},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.47149962186813354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35892295837402344},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20430579781532288},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1819300651550293},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.10343635082244873}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8575938940048218},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.8013383150100708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7903551459312439},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132169008255005},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6220210790634155},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5854747295379639},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5480945706367493},{"id":"https://openalex.org/C94957134","wikidata":"https://www.wikidata.org/wiki/Q82990","display_name":"Numerical digit","level":2,"score":0.5262888073921204},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.47149962186813354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35892295837402344},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20430579781532288},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1819300651550293},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.10343635082244873},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/icassp.2010.5495128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4699999988079071},{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W263640664","https://openalex.org/W1494802605","https://openalex.org/W1925046873","https://openalex.org/W2053292927","https://openalex.org/W2072170479","https://openalex.org/W2102070801","https://openalex.org/W2156216400","https://openalex.org/W4285719527","https://openalex.org/W4390911713","https://openalex.org/W6608246541"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2163874654"],"abstract_inverted_index":{"Mandarin":[0,80],"digit":[1],"string":[2],"recognition":[3,22],"(MDSR)":[4],"is":[5,42,49,71,117],"a":[6,18,61,66],"challenge":[7],"because":[8],"there":[9],"exist":[10],"many":[11],"difficulties":[12],"in":[13,51,60],"acoustic":[14,77],"discrimination":[15,78],"for":[16],"such":[17],"small":[19],"vocabulary":[20],"speech":[21],"task.":[23],"In":[24,110],"this":[25],"paper,":[26],"we":[27],"propose":[28],"to":[29,44,74,107],"improve":[30,75,91],"MDSR":[31,53],"performance":[32],"by":[33,55,119],"using":[34],"duration":[35,46,87],"and":[36,48,88,94],"pitch":[37,68,89],"information.":[38],"Speech":[39],"rate":[40,116],"dispersion":[41],"used":[43],"involve":[45],"knowledge":[47],"incorporated":[50],"the":[52,57,76,92,95,111,113],"system":[54],"rescoring":[56],"N-best":[58],"candidates":[59],"two-pass":[62],"framework.":[63],"estimated":[64],"with":[65],"robust":[67,106],"extraction":[69],"method":[70],"also":[72],"adopted":[73],"among":[79],"digits.":[81],"The":[82],"experimental":[83],"results":[84],"show":[85],"both":[86],"significantly":[90],"performance,":[93],"combination":[96],"of":[97],"them":[98],"gives":[99],"further":[100],"improvement.":[101],"Moreover,":[102],"our":[103],"methods":[104],"are":[105],"background":[108],"noise.":[109],"evaluation,":[112],"sentence":[114],"error":[115],"reduced":[118],"50.43%":[120],"on":[121],"average":[122],"over":[123],"different":[124],"SNR":[125],"conditions.":[126]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}