{"id":"https://openalex.org/W4372266896","doi":"https://doi.org/10.1109/icassp49357.2023.10094639","title":"EfficientSpeech: An On-Device Text to Speech Model","display_name":"EfficientSpeech: An On-Device Text to Speech Model","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266896","doi":"https://doi.org/10.1109/icassp49357.2023.10094639"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5042632410","display_name":"Rowel Atienza","orcid":"https://orcid.org/0000-0002-8830-2534"},"institutions":[{"id":"https://openalex.org/I4210117802","display_name":"Institute of Electronics","ror":"https://ror.org/0299eyn73","country_code":"BG","type":"nonprofit","lineage":["https://openalex.org/I24768866","https://openalex.org/I4210117802"]},{"id":"https://openalex.org/I103911934","display_name":"University of the Philippines System","ror":"https://ror.org/02hqkr514","country_code":"PH","type":"education","lineage":["https://openalex.org/I103911934"]}],"countries":["BG","PH"],"is_corresponding":true,"raw_author_name":"Rowel Atienza","raw_affiliation_strings":["University of the Philippines,Electrical and Electronics Engineering Institute and AI Graduate Program","Electrical and Electronics Engineering Institute and AI Graduate Program, University of the Philippines"],"affiliations":[{"raw_affiliation_string":"University of the Philippines,Electrical and Electronics Engineering Institute and AI Graduate Program","institution_ids":["https://openalex.org/I4210117802"]},{"raw_affiliation_string":"Electrical and Electronics Engineering Institute and AI Graduate Program, University of the Philippines","institution_ids":["https://openalex.org/I103911934"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5042632410"],"corresponding_institution_ids":["https://openalex.org/I103911934","https://openalex.org/I4210117802"],"apc_list":null,"apc_paid":null,"fwci":1.226,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82735426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9991000294685364,"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":0.9975000023841858,"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":0.7648385763168335},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6416370868682861},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5611516237258911},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5486149191856384},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5101547837257385},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49986743927001953},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4814288318157196},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.46495330333709717},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4218772053718567},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4137396812438965},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41308796405792236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27911776304244995},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13528084754943848},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1307438313961029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648385763168335},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6416370868682861},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5611516237258911},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5486149191856384},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5101547837257385},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49986743927001953},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4814288318157196},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.46495330333709717},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4218772053718567},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4137396812438965},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41308796405792236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27911776304244995},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13528084754943848},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1307438313961029},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W349236604","https://openalex.org/W1563089615","https://openalex.org/W1901129140","https://openalex.org/W2747874407","https://openalex.org/W2899663614","https://openalex.org/W2903739847","https://openalex.org/W2908510526","https://openalex.org/W2963691546","https://openalex.org/W2964243274","https://openalex.org/W2974231335","https://openalex.org/W3033411150","https://openalex.org/W3034949308","https://openalex.org/W3092028330","https://openalex.org/W3150572638","https://openalex.org/W3160919572","https://openalex.org/W3169905056","https://openalex.org/W3197649190","https://openalex.org/W3203394408","https://openalex.org/W3211490618","https://openalex.org/W4210684870","https://openalex.org/W4286950013","https://openalex.org/W4385245566","https://openalex.org/W6633684334","https://openalex.org/W6639824700","https://openalex.org/W6739901393","https://openalex.org/W6749489859","https://openalex.org/W6755977528","https://openalex.org/W6757817989","https://openalex.org/W6767671539","https://openalex.org/W6778823374","https://openalex.org/W6780226713","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6797399245","https://openalex.org/W6801525743","https://openalex.org/W6802142237","https://openalex.org/W6803464654","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2899676847","https://openalex.org/W596245619","https://openalex.org/W2254895521"],"abstract_inverted_index":{"State":[0],"of":[1,27,104,109,126],"the":[2,31,105],"art":[3],"(SOTA)":[4],"neural":[5,67],"text":[6],"to":[7,30,49,143],"speech":[8,35,52,73],"(TTS)":[9],"models":[10,17,44,114],"can":[11],"generate":[12],"natural-sounding":[13],"synthetic":[14],"voices.":[15],"These":[16],"are":[18,45],"characterized":[19],"by":[20],"large":[21],"memory":[22],"footprints":[23],"and":[24,56,96,107],"substantial":[25],"number":[26],"operations":[28],"due":[29],"long-standing":[32],"focus":[33],"on":[34,54,74,128],"quality":[36,140],"with":[37],"cloud":[38],"inference":[39],"in":[40,78,111,138],"mind.":[41],"Neural":[42],"TTS":[43,68],"generally":[46],"not":[47],"designed":[48],"perform":[50],"standalone":[51],"syntheses":[53],"resource-constrained":[55],"no":[57],"Internet":[58],"access":[59],"edge":[60],"devices.":[61],"In":[62],"this":[63],"work,":[64],"an":[65,75,120,129],"efficient":[66],"called":[69],"EfficientSpeech":[70,82,92,118],"that":[71],"synthesizes":[72],"ARM":[76],"CPU":[77],"real-time":[79,124],"is":[80],"proposed.":[81],"uses":[83],"a":[84,90,135],"shallow":[85],"non-autoregressive":[86],"pyramid-structure":[87],"transformer":[88],"forming":[89],"U-Network.":[91],"has":[93],"266k":[94],"parameters":[95],"consumes":[97],"90":[98],"MFLOPS":[99],"only":[100,134],"or":[101],"about":[102],"1%":[103],"size":[106],"amount":[108],"computation":[110],"modern":[112],"compact":[113],"such":[115],"as":[116,141],"Mixer-TTS.":[117],"achieves":[119],"average":[121],"mel":[122],"generation":[123],"factor":[125],"104.3":[127],"RPi4.":[130],"Human":[131],"evaluation":[132],"shows":[133],"slight":[136],"degradation":[137],"audio":[139],"compared":[142],"FastSpeech2.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-02-24T08:05:00.420983","created_date":"2025-10-10T00:00:00"}