{"id":"https://openalex.org/W3160248152","doi":"https://doi.org/10.1109/icassp39728.2021.9414809","title":"Multi-Rate Attention Architecture for Fast Streamable Text-to-Speech Spectrum Modeling","display_name":"Multi-Rate Attention Architecture for Fast Streamable Text-to-Speech Spectrum Modeling","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160248152","doi":"https://doi.org/10.1109/icassp39728.2021.9414809","mag":"3160248152"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5102191169","display_name":"Qing He","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Qing He","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085174046","display_name":"Zhiping Xiu","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Zhiping Xiu","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022133847","display_name":"Thilo Koehler","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Thilo Koehler","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057239023","display_name":"Jilong Wu","orcid":"https://orcid.org/0009-0007-8000-347X"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jilong Wu","raw_affiliation_strings":["Facebook AI"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102191169"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":0.9518,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7969112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5689","last_page":"5693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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/T11309","display_name":"Music and Audio Processing","score":0.9944999814033508,"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":0.8192283511161804},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7500225901603699},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6954982280731201},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6953548192977905},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6085290908813477},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5323161482810974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5162532329559326},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5002763271331787},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.47958794236183167},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.43536412715911865},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4273957908153534},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3667498826980591},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18174460530281067},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16804224252700806},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11569806933403015}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192283511161804},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7500225901603699},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6954982280731201},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6953548192977905},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6085290908813477},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5323161482810974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5162532329559326},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5002763271331787},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.47958794236183167},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.43536412715911865},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4273957908153534},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3667498826980591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18174460530281067},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16804224252700806},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11569806933403015},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.550000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W1920484244","https://openalex.org/W2519091744","https://openalex.org/W2591724398","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963300588","https://openalex.org/W2963403868","https://openalex.org/W2963405869","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2970730223","https://openalex.org/W3006108364","https://openalex.org/W4298580827","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6736996214","https://openalex.org/W6739901393","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6763832098","https://openalex.org/W6773966927"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W4283822356","https://openalex.org/W1950940422","https://openalex.org/W2129146436","https://openalex.org/W2032507829","https://openalex.org/W2147282173","https://openalex.org/W1541810870"],"abstract_inverted_index":{"Typical":[0],"high":[1,50,129],"quality":[2,51,131],"text-to-speech":[3],"(TTS)":[4],"systems":[5],"today":[6],"use":[7,86],"a":[8,12,21,95,108,120],"two-stage":[9],"architecture,":[10],"with":[11,37,65],"spectrum":[13,30],"model":[14],"stage":[15,23],"that":[16,24,99],"generates":[17,25],"spectral":[18],"frames":[19],"and":[20,61,80,103,113,141,151],"vocoder":[22],"the":[26,34,101,116,145,154],"actual":[27],"audio.":[28],"High-quality":[29],"models":[31,47],"usually":[32],"incorporate":[33],"encoder-decoder":[35],"architecture":[36,98,127],"self-attention":[38],"or":[39],"bi-directional":[40],"long":[41],"short-term":[42],"(BLSTM)":[43],"units.":[44],"While":[45],"these":[46],"can":[48],"produce":[49],"speech,":[52],"they":[53],"often":[54],"incur":[55],"O(L)":[56],"increase":[57],"in":[58,87,119],"both":[59,149],"latency":[60,102,150],"real-time":[62,88,167],"factor":[63],"(RTF)":[64],"respect":[66],"to":[67,77,136],"input":[68,161],"length":[69],"L.":[70],"In":[71,90],"other":[72],"words,":[73],"longer":[74,78],"inputs":[75],"leads":[76],"delay":[79],"slower":[81],"synthesis":[82],"speed,":[83],"limiting":[84],"its":[85],"applications.":[89,168],"this":[91],"paper,":[92],"we":[93],"propose":[94],"multi-rate":[96],"attention":[97,117],"breaks":[100],"RTF":[104,143,152],"bottlenecks":[105],"by":[106],"computing":[107],"compact":[109],"representation":[110],"during":[111,123],"encoding":[112],"recurrently":[114],"generating":[115],"vector":[118],"streaming":[121],"manner":[122],"decoding.":[124],"The":[125],"proposed":[126,155],"achieves":[128],"audio":[130],"(MOS":[132],"of":[133,153,160],"4.31":[134],"compared":[135],"groundtruth":[137],"4.48),":[138],"low":[139,142],"latency,":[140],"at":[144],"same":[146],"time.":[147],"Meanwhile,":[148],"system":[156],"stay":[157],"constant":[158],"regardless":[159],"lengths,":[162],"making":[163],"it":[164],"ideal":[165],"for":[166]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}