{"id":"https://openalex.org/W3117216601","doi":"https://doi.org/10.1109/o-cocosda50338.2020.9295010","title":"Prosodic Information-Assisted DNN-based Mandarin Spontaneous-Speech Recognition","display_name":"Prosodic Information-Assisted DNN-based Mandarin Spontaneous-Speech Recognition","publication_year":2020,"publication_date":"2020-11-05","ids":{"openalex":"https://openalex.org/W3117216601","doi":"https://doi.org/10.1109/o-cocosda50338.2020.9295010","mag":"3117216601"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda50338.2020.9295010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda50338.2020.9295010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5036696807","display_name":"Yu-Chih Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Chih Deng","raw_affiliation_strings":["ECE Department, NCTU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, NCTU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055026910","display_name":"Cheng-Hsin Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng-Hsin Lin","raw_affiliation_strings":["ECE Department, NCTU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, NCTU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082271172","display_name":"Yuan\u2010Fu Liao","orcid":"https://orcid.org/0000-0003-0191-2178"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan-Fu Liao","raw_affiliation_strings":["EE Department, NTUT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EE Department, NTUT","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071941088","display_name":"Yih\u2010Ru Wang","orcid":"https://orcid.org/0000-0002-4483-1418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yih-Ru Wang","raw_affiliation_strings":["ECE Department, NCTU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, NCTU","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015529786","display_name":"Sin\u2010Horng Chen","orcid":"https://orcid.org/0000-0002-9820-2318"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sin-Horng Chen","raw_affiliation_strings":["ECE Department, NCTU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, NCTU","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.115,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41516975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"17","issue":null,"first_page":"134","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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":0.8022133111953735},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7931286096572876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7562289237976074},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.7050414681434631},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.644789457321167},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6316468715667725},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48373985290527344},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44962674379348755},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41890421509742737},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.4117628335952759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3826475441455841},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11347997188568115},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06697121262550354}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8022133111953735},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7931286096572876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562289237976074},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7050414681434631},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.644789457321167},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6316468715667725},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48373985290527344},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44962674379348755},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41890421509742737},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.4117628335952759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3826475441455841},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11347997188568115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06697121262550354},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda50338.2020.9295010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda50338.2020.9295010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2056250865","https://openalex.org/W2080005694","https://openalex.org/W2114804338","https://openalex.org/W2119340951","https://openalex.org/W2181604756","https://openalex.org/W2401714573","https://openalex.org/W2473213690","https://openalex.org/W2474824677","https://openalex.org/W2500011979","https://openalex.org/W2533523411","https://openalex.org/W2750562505","https://openalex.org/W2786459654","https://openalex.org/W2799473636","https://openalex.org/W2802201485","https://openalex.org/W2802422770","https://openalex.org/W2888867175","https://openalex.org/W2889152503","https://openalex.org/W2889477554","https://openalex.org/W2943395818","https://openalex.org/W2963217176","https://openalex.org/W2963266252","https://openalex.org/W2972841547","https://openalex.org/W2982471419","https://openalex.org/W2998704965","https://openalex.org/W3101648800","https://openalex.org/W4256161595","https://openalex.org/W6675977553","https://openalex.org/W6677629938","https://openalex.org/W6680532216","https://openalex.org/W6685728298","https://openalex.org/W6713011556","https://openalex.org/W6720877245"],"related_works":["https://openalex.org/W2393887907","https://openalex.org/W2347443630","https://openalex.org/W2481138693","https://openalex.org/W2388826840","https://openalex.org/W2379831327","https://openalex.org/W2386691339","https://openalex.org/W2365805939","https://openalex.org/W2287147624","https://openalex.org/W156219719","https://openalex.org/W2163874654"],"abstract_inverted_index":{"This":[0,42,138],"paper":[1],"continues":[2],"the":[3,31,66,75,78,100,107,123,141,149],"method":[4,143],"proposed":[5,142],"in":[6],"[1]":[7,116],"and":[8,37,58,64,72,90,127,131],"updates":[9],"its":[10],"traditional":[11],"HMM-based":[12],"ASR":[13],"to":[14,21,29,62,117],"state-of-the-art":[15,23],"DNN-based":[16,24],"ASR.":[17],"Use":[18],"prosodic":[19,48,57,59,91],"information":[20],"assist":[22],"Mandarin":[25,152],"spontaneous-speech":[26,153],"recognition,":[27],"especially":[28],"alleviate":[30],"serious":[32],"interference":[33],"of":[34,52,81,151],"annoying":[35],"disfluencies":[36],"paralinguistic":[38],"phenomena":[39],"during":[40],"decoding.":[41],"approach":[43],"adopts":[44],"a":[45],"sophisticated":[46],"hierarchical":[47],"model":[49],"(HPM)":[50],"made":[51],"several":[53],"break-syntax,":[54],"break-acoustic,":[55],"syllable":[56],"state":[60,92],"models":[61],"rescore":[63],"improve":[65],"TDNN-f+RNNLM-based":[67],"1st":[68],"pass":[69],"decoding":[70],"output":[71],"generate,":[73],"at":[74],"same":[76],"time,":[77],"word,":[79],"Part":[80],"Speech":[82],"(POS),":[83],"Punctuation":[84],"Mark":[85],"(PM),":[86],"tone,":[87],"break":[88],"type,":[89],"tags":[93],"for":[94],"further":[95],"use.":[96],"Experimental":[97],"results":[98],"showed":[99],"HPM-based":[101],"system":[102],"not":[103],"only":[104],"dramatically":[105],"reduced":[106],"word":[108],"error":[109,133],"rate":[110],"from":[111],"previous":[112],"best":[113],"value:":[114],"41.8%":[115],"21.2%.":[118],"It":[119],"also":[120],"detected":[121],"well":[122],"underlying":[124],"POS,":[125],"PMs,":[126],"tones":[128],"(10.9%,":[129],"12.6%,":[130],"2.3%":[132],"rates":[134],"were":[135],"achieved,":[136],"respectively).":[137],"confirms":[139],"that":[140],"is":[144],"very":[145],"promising":[146],"on":[147],"tackling":[148],"task":[150],"recognition.":[154]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}