{"id":"https://openalex.org/W2937909162","doi":"https://doi.org/10.1109/icassp.2019.8682861","title":"Enhancing Hybrid Self-attention Structure with Relative-position-aware Bias for Speech Synthesis","display_name":"Enhancing Hybrid Self-attention Structure with Relative-position-aware Bias for Speech Synthesis","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937909162","doi":"https://doi.org/10.1109/icassp.2019.8682861","mag":"2937909162"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"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":true,"raw_author_name":"Shan Yang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"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/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006486310","display_name":"Kang Shi-ying","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiying Kang","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"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 Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101736420"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.9602,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89546051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6910","last_page":"6914"},"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/T12031","display_name":"Speech and dialogue systems","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.6196641325950623},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5456075072288513},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5440887212753296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3470364511013031},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07722371816635132}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6196641325950623},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5456075072288513},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5440887212753296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3470364511013031},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07722371816635132},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W2043003570","https://openalex.org/W2102003408","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2515943672","https://openalex.org/W2519091744","https://openalex.org/W2613904329","https://openalex.org/W2749651610","https://openalex.org/W2766812927","https://openalex.org/W2767052532","https://openalex.org/W2866343820","https://openalex.org/W2884852625","https://openalex.org/W2892140764","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2933485668","https://openalex.org/W2949382160","https://openalex.org/W2959575783","https://openalex.org/W2962911926","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963925437","https://openalex.org/W2964045208","https://openalex.org/W2964243274","https://openalex.org/W2964265128","https://openalex.org/W2964302946","https://openalex.org/W2964308564","https://openalex.org/W3026414669","https://openalex.org/W3142087749","https://openalex.org/W4385245566","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6745697700","https://openalex.org/W6746700228","https://openalex.org/W6753640285","https://openalex.org/W6754925833","https://openalex.org/W6756197946"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Compared":[0],"with":[1,60,112,124,140,150],"the":[2,9,24,53,71,79,82,90,99,113,121,143,147],"conventional":[3],"\"front-end\"-\"back-end\"-":[4],"\"vocoder\"":[5],"structure,":[6],"based":[7,43],"on":[8,44,89],"attention":[10,80],"mechanism,":[11],"end-to-end":[12,36],"speech":[13],"synthesis":[14],"systems":[15],"directly":[16],"train":[17],"and":[18,55],"synthesize":[19],"from":[20],"text":[21],"sequence":[22,27,85],"to":[23,48,81,97],"acoustic":[25],"feature":[26],"as":[28],"a":[29,32,105],"whole.":[30],"Recently,":[31],"more":[33,91],"calculation":[34],"efficient":[35],"architecture":[37],"named":[38],"transformer,":[39],"which":[40,109],"is":[41],"solely":[42],"self-attention,":[45],"was":[46],"proposed":[47,122,144],"model":[49],"global":[50],"dependencies":[51],"between":[52],"input":[54,84],"output":[56],"sequences.":[57],"However,":[58],"although":[59],"many":[61],"advantages,":[62],"transformer":[63],"lacks":[64],"position":[65],"information":[66],"in":[67,75],"its":[68],"structure.":[69],"Moreover,":[70],"weighted":[72],"sum":[73],"form":[74],"self-attention":[76,107,111,138],"may":[77],"disperse":[78],"whole":[83],"other":[86],"than":[87,156],"focusing":[88],"important":[92],"neighbouring":[93],"positions.":[94],"In":[95],"order":[96],"solve":[98],"above":[100],"problems,":[101],"this":[102],"paper":[103],"introduces":[104],"hybrid":[106,137],"structure":[108,123,139],"combines":[110],"recurrent":[114],"neural":[115],"networks":[116],"(RNNs).":[117],"We":[118],"further":[119],"enhance":[120],"relative-position-aware":[125,141],"biases.":[126],"Mean":[127],"opinion":[128],"score":[129,154],"(MOS)":[130],"test":[131],"results":[132],"indicate":[133],"that":[134],"by":[135],"enhancing":[136],"biases,":[142],"system":[145],"achieves":[146],"best":[148],"performance":[149],"only":[151],"0.11":[152],"MOS":[153],"lower":[155],"natural":[157],"recording.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}