乐胖代购免代理版

{"id":"https://openalex.org/W2937870435","doi":"https://doi.org/10.1109/icassp.2019.8683682","title":"Multi-speaker Emotional Acoustic Modeling for CNN-based Speech Synthesis","display_name":"Multi-speaker Emotional Acoustic Modeling for CNN-based Speech Synthesis","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2937870435","doi":"https://doi.org/10.1109/icassp.2019.8683682","mag":"2937870435"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683682","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5081997471","display_name":"Heejin Choi","orcid":"https://orcid.org/0000-0001-5093-2859"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heejin Choi","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100690663","display_name":"Sangjun Park","orcid":"https://orcid.org/0009-0005-6103-7688"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangjun Park","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056435660","display_name":"Jinuk Park","orcid":"https://orcid.org/0000-0002-9436-9639"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinuk Park","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046372250","display_name":"Minsoo Hahn","orcid":"https://orcid.org/0000-0003-1953-6078"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsoo Hahn","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.617,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":32,"citation_normalized_percentile":{"value":0.999907,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6950","last_page":"6954"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition Technology","score":0.9999,"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 Technology","score":0.9999,"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":"Audio Signal Classification and Analysis","score":0.997,"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 Enhancement Techniques","score":0.9933,"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/spectrogram","display_name":"Spectrogram","score":0.68569875},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5600515},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech Enhancement","score":0.558545},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"Acoustic Modeling","score":0.557933},{"id":"https://openalex.org/keywords/end-to-end-speech-recognition","display_name":"End-to-End Speech Recognition","score":0.554704},{"id":"https://openalex.org/keywords/statistical-language-modeling","display_name":"Statistical Language Modeling","score":0.539125},{"id":"https://openalex.org/keywords/audio-visual-speech-recognition","display_name":"Audio-Visual Speech Recognition","score":0.534225},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.521731},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4817136}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7307759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7252985},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.70027786},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.68569875},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5600515},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5291959},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.521731},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.50358814},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4905426},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48181334},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4817136},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4178539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36370337},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.084429264},{"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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683682","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":27,"referenced_works":["https://openalex.org/W1492383498","https://openalex.org/W1522301498","https://openalex.org/W1576227399","https://openalex.org/W1836465849","https://openalex.org/W2064675550","https://openalex.org/W2102003408","https://openalex.org/W2103869314","https://openalex.org/W2120847449","https://openalex.org/W2157331557","https://openalex.org/W2471520273","https://openalex.org/W2494654097","https://openalex.org/W2516321201","https://openalex.org/W2516559027","https://openalex.org/W2562274522","https://openalex.org/W2567070169","https://openalex.org/W2749651610","https://openalex.org/W2785364623","https://openalex.org/W2787378487","https://openalex.org/W2794490148","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963840672","https://openalex.org/W2963927338","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W4295731579","https://openalex.org/W88081813"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W40885451","https://openalex.org/W2946856121","https://openalex.org/W2535215250","https://openalex.org/W2433276473","https://openalex.org/W2206035908","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W1914543332","https://openalex.org/W1813881148"],"abstract_inverted_index":{"In":[0,55],"this":[1],"paper,":[2],"we":[3,22,44,66],"investigate":[4],"multi-speaker":[5,101],"emotional":[6,41,102],"acoustic":[7],"modeling":[8],"methods":[9],"for":[10],"convolutional":[11],"neural":[12],"network":[13],"(CNN)":[14],"based":[15],"speech":[16,26,81,103],"synthesis":[17,27,82,104],"system.":[18],"For":[19],"emotion":[20,46,53,88,111,131],"modeling,":[21],"extend":[23],"to":[24,57],"the":[25,100],"system":[28],"that":[29,99],"learns":[30],"a":[31,39,62],"latent":[32],"embedding":[33,74,109],"space":[34],"of":[35,126],"emotion,":[36],"derived":[37],"from":[38,113],"desired":[40],"identity,":[42],"and":[43,48,75,87,90,110,130],"use":[45,67],"code":[47],"mel-frequency":[49],"spectrogram":[50,115],"as":[51,71],"an":[52],"identity.":[54],"order":[56],"model":[58],"speaker":[59,68,73,76,85,108,128],"variation":[60],"in":[61,124],"text-to-speech":[63],"(TTS)":[64],"system,":[65],"representations":[69],"such":[70],"trainable":[72,107],"code.":[77],"We":[78],"have":[79,97],"implemented":[80],"systems":[83],"combining":[84],"representation":[86,89,112],"compared":[91,120],"them":[92],"by":[93],"experiments.":[94],"Experimental":[95],"results":[96],"demonstrated":[98],"approach":[105],"using":[106],"mel":[114],"achieves":[116],"higher":[117],"performance":[118],"when":[119],"with":[121],"other":[122],"approaches":[123],"terms":[125],"naturalness,":[127],"similarity,":[129],"similarity.":[132]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2937870435","counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4}],"updated_date":"2024-12-03T16:05:03.580747","created_date":"2019-04-25"}