{"id":"https://openalex.org/W2991556167","doi":"https://doi.org/10.1145/3364908.3365291","title":"Automatic Pitch Accent Detection Using Long Short-Term Memory Neural Networks","display_name":"Automatic Pitch Accent Detection Using Long Short-Term Memory Neural Networks","publication_year":2019,"publication_date":"2019-09-20","ids":{"openalex":"https://openalex.org/W2991556167","doi":"https://doi.org/10.1145/3364908.3365291","mag":"2991556167"},"language":"en","primary_location":{"id":"doi:10.1145/3364908.3365291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3364908.3365291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Symposium on Signal Processing Systems","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/A5100301343","display_name":"Yizhi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yizhi Wu","raw_affiliation_strings":["College of Information Science and Technology, Donghua University, China Shanghai"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Donghua University, China Shanghai","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056255679","display_name":"Sha Li","orcid":"https://orcid.org/0000-0001-6238-7544"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sha Li","raw_affiliation_strings":["College of Information Science and Technology, Donghua University, China Shanghai"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Donghua University, China Shanghai","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455569","display_name":"Hongyan Li","orcid":"https://orcid.org/0000-0001-7174-2851"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyan Li","raw_affiliation_strings":["College of Information Science and Technology, Donghua University, China Shanghai"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Donghua University, China Shanghai","institution_ids":["https://openalex.org/I181326427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100301343"],"corresponding_institution_ids":["https://openalex.org/I181326427"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72132407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9959999918937683,"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":0.9932000041007996,"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/computer-science","display_name":"Computer science","score":0.7626464366912842},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7555022239685059},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.752903938293457},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6456947922706604},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6225072741508484},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.5977619886398315},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5738903880119324},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5714919567108154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.532588005065918},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.43325936794281006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3482024073600769}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626464366912842},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7555022239685059},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.752903938293457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6456947922706604},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6225072741508484},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.5977619886398315},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5738903880119324},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5714919567108154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.532588005065918},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.43325936794281006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3482024073600769},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3364908.3365291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3364908.3365291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Symposium on Signal Processing Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W44259984","https://openalex.org/W57885259","https://openalex.org/W1861945760","https://openalex.org/W2049950192","https://openalex.org/W2058412794","https://openalex.org/W2064675550","https://openalex.org/W2070514005","https://openalex.org/W2093476462","https://openalex.org/W2121765613","https://openalex.org/W2125689567","https://openalex.org/W2146423738","https://openalex.org/W2148841122","https://openalex.org/W2159372275","https://openalex.org/W2166317648","https://openalex.org/W2170979168","https://openalex.org/W2398044918","https://openalex.org/W2402812677","https://openalex.org/W2406264770","https://openalex.org/W2750712356","https://openalex.org/W2770743368","https://openalex.org/W6743384451"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W2396586136","https://openalex.org/W2071315723","https://openalex.org/W2507083698","https://openalex.org/W2465473908","https://openalex.org/W49590631","https://openalex.org/W2370788932","https://openalex.org/W2474947928","https://openalex.org/W2967415048"],"abstract_inverted_index":{"Prosody":[0],"detection":[1,143,158],"is":[2,27,150],"gaining":[3],"increasingly":[4],"popularity":[5],"in":[6,16,61],"the":[7,81,94,131,153],"domain":[8],"of":[9,13,31,37,83,96,147,155],"prosody":[10,32],"research":[11],"because":[12],"its":[14],"significance":[15],"Text":[17],"to":[18,72,80,130],"Sound,":[19],"Computer-aided":[20],"pronunciation":[21],"training":[22],"(CAPT),":[23],"etc.":[24],"Pitch":[25],"accent":[26,63,106,142],"an":[28,145],"important":[29],"part":[30],"and":[33,40,74,112,118],"many":[34],"recognition":[35],"models":[36],"both":[38],"static":[39],"dynamic":[41],"have":[42,58],"been":[43,59],"investigated":[44],"for":[45,103,140],"automatic":[46,104],"labeling":[47],"it.":[48],"Recently,":[49],"artificial":[50],"neural":[51,68,101],"networks,":[52],"especially":[53],"Recurrent":[54],"Neural":[55],"Networks":[56],"(RNNs)":[57],"applied":[60],"pitch":[62,105,141],"detection.":[64,107],"However,":[65],"traditional":[66],"recurrent":[67],"networks":[69,102],"are":[70],"unable":[71],"learn":[73],"remember":[75],"over":[76],"long":[77],"sequences":[78],"due":[79],"issue":[82],"back-propagated":[84],"error":[85],"decay.":[86],"To":[87],"solve":[88],"this":[89,91],"problem,":[90],"paper":[92,109],"investigates":[93],"use":[95],"Long":[97],"Short-Term":[98],"Memory":[99],"(LSTM)":[100],"This":[108],"encodes":[110],"lexical":[111],"syntactic":[113],"features":[114,122,128],"as":[115],"binary":[116],"variables":[117],"uses":[119],"syllable-based":[120],"acoustic":[121],"including":[123],"syllable":[124,126],"duration,":[125],"energy,":[127],"related":[129],"fundamental":[132],"frequency.":[133],"Our":[134],"experimental":[135],"results":[136,154],"show":[137],"that":[138],"LSTM-RNNs":[139],"achieves":[144],"accuracy":[146],"89.0%,":[148],"which":[149],"better":[151],"than":[152],"using":[156],"classical":[157],"methods":[159],"by":[160],"about":[161],"83.2%.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}