{"id":"https://openalex.org/W2963078821","doi":"https://doi.org/10.1109/asru.2015.7404780","title":"Automatic prosody prediction for Chinese speech synthesis using BLSTM-RNN and embedding features","display_name":"Automatic prosody prediction for Chinese speech synthesis using BLSTM-RNN and embedding features","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2963078821","doi":"https://doi.org/10.1109/asru.2015.7404780","mag":"2963078821"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","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/A5113730802","display_name":"Chuang Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Ding","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Software and Microelectronics, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101718582","display_name":"Jie Yan","orcid":"https://orcid.org/0000-0001-7980-1078"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Yan","raw_affiliation_strings":["School of Software and Microelectronics, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058759011","display_name":"Weini Zhang","orcid":"https://orcid.org/0000-0001-8509-3039"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weini Zhang","raw_affiliation_strings":["School of Software and Microelectronics, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086000078","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-3087-242X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["School of Software and Microelectronics, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"98","last_page":"102"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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/prosody","display_name":"Prosody","score":0.8872132301330566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830356955528259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7495434284210205},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7003969550132751},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5998711585998535},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5357989072799683},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5278282761573792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5057547092437744},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49065008759498596},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.4869319200515747},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.4807124435901642},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.46170762181282043},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3914406895637512},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3897213935852051},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.25063812732696533},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.21403566002845764}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8872132301330566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830356955528259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7495434284210205},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7003969550132751},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5998711585998535},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5357989072799683},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5278282761573792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5057547092437744},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49065008759498596},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.4869319200515747},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.4807124435901642},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.46170762181282043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3914406895637512},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3897213935852051},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25063812732696533},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.21403566002845764},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2015.7404780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W9334768","https://openalex.org/W178594153","https://openalex.org/W304834817","https://openalex.org/W1540777719","https://openalex.org/W1674799117","https://openalex.org/W2005708641","https://openalex.org/W2008838899","https://openalex.org/W2049950192","https://openalex.org/W2064675550","https://openalex.org/W2103518983","https://openalex.org/W2104012431","https://openalex.org/W2131774270","https://openalex.org/W2141599568","https://openalex.org/W2147880316","https://openalex.org/W2153579005","https://openalex.org/W2158899491","https://openalex.org/W2162433174","https://openalex.org/W2251736053","https://openalex.org/W2251811146","https://openalex.org/W2252225757","https://openalex.org/W2254292464","https://openalex.org/W2403419258","https://openalex.org/W2952230511","https://openalex.org/W2998704965","https://openalex.org/W4285719527","https://openalex.org/W4294170691","https://openalex.org/W6637157234","https://openalex.org/W6680532216","https://openalex.org/W6680890276","https://openalex.org/W6682082992","https://openalex.org/W6682691769","https://openalex.org/W6683738474","https://openalex.org/W6691585438","https://openalex.org/W6691783218","https://openalex.org/W6691808304","https://openalex.org/W6692030067","https://openalex.org/W6713622347"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W3149582125","https://openalex.org/W2946856121","https://openalex.org/W2465421051","https://openalex.org/W1914543332","https://openalex.org/W2370805772","https://openalex.org/W2181715843","https://openalex.org/W652196294","https://openalex.org/W2395605663","https://openalex.org/W1984347656"],"abstract_inverted_index":{"Prosody":[0],"affects":[1],"the":[2,24,79,91],"naturalness":[3],"and":[4,23,66],"intelligibility":[5],"of":[6],"speech.":[7],"However,":[8],"automatic":[9],"prosody":[10],"prediction":[11],"from":[12,53,86],"text":[13,88],"for":[14],"Chinese":[15,54],"speech":[16],"synthesis":[17],"is":[18],"still":[19],"a":[20],"great":[21],"challenge":[22],"traditional":[25],"conditional":[26],"random":[27],"fields":[28],"(CRF)":[29],"based":[30],"method":[31],"always":[32],"heavily":[33],"relies":[34],"on":[35],"feature":[36,58],"engineering.":[37,59],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"to":[43,47],"use":[44],"neural":[45],"networks":[46],"predict":[48],"prosodic":[49],"boundary":[50],"labels":[51],"directly":[52],"characters":[55],"without":[56],"any":[57],"Experimental":[60],"results":[61],"show":[62],"that":[63],"stacking":[64],"feed-forward":[65],"bidirectional":[67],"long":[68],"short-term":[69],"memory":[70],"(BLSTM)":[71],"recurrent":[72],"network":[73],"layers":[74],"achieves":[75],"superior":[76],"performance":[77],"over":[78],"CRF-based":[80],"method.":[81],"The":[82],"embedding":[83],"features":[84],"learned":[85],"raw":[87],"further":[89],"enhance":[90],"performance.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}