{"id":"https://openalex.org/W7148596233","doi":"https://doi.org/10.1109/asru65441.2025.11434621","title":"Llasa+: Free Lunch for Accelerated and Streaming Llama-Based Speech Synthesis","display_name":"Llasa+: Free Lunch for Accelerated and Streaming Llama-Based Speech Synthesis","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148596233","doi":"https://doi.org/10.1109/asru65441.2025.11434621"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132827557","display_name":"Wenjie Tian","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":true,"raw_author_name":"Wenjie Tian","raw_affiliation_strings":["Northwestern Polytechnical University,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"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":"Xinfa Zhu","raw_affiliation_strings":["Northwestern Polytechnical University,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100583264","display_name":"HanKe Xie","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":"Hanke Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132801358","display_name":"Zhen Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhen Ye","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132830555","display_name":"Wei Xue","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":"Wei Xue","raw_affiliation_strings":["Northwestern Polytechnical University,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132823306","display_name":"Lei Xie","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":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5132827557"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86783927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6550999879837036,"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":0.6550999879837036,"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":0.22840000689029694,"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/T11448","display_name":"Face recognition and analysis","score":0.015799999237060547,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speedup","display_name":"Speedup","score":0.8083000183105469},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7289999723434448},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5784000158309937},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5629000067710876},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4693000018596649},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.42239999771118164},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.3562999963760376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8790000081062317},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8083000183105469},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7289999723434448},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5784000158309937},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5629000067710876},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38830000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35679998993873596},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32179999351501465},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2669999897480011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5778786540031433,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2972359262","https://openalex.org/W4412945617","https://openalex.org/W4416036510"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,36,86],"text-to-speech":[3],"(TTS)":[4],"has":[5],"achieved":[6],"impressive":[7],"naturalness":[8],"and":[9,26,39,52,173],"flexibility,":[10],"especially":[11],"with":[12,44],"the":[13,45,62,74,80,108,113,160],"development":[14],"of":[15],"large":[16],"language":[17],"model":[18,55,81],"(LLM)-based":[19],"approaches.":[20],"However,":[21],"existing":[22],"autoregressive":[23],"(AR)":[24],"structures":[25],"large-scale":[27],"models,":[28],"such":[29],"as":[30],"Llasa,":[31],"still":[32],"face":[33],"significant":[34],"challenges":[35],"inference":[37],"latency":[38],"streaming":[40,53,134],"synthesis.":[41],"To":[42],"deal":[43],"limitations,":[46],"we":[47,65,100,127],"introduce":[48,66],"Llasa+,":[49],"an":[50],"accelerated":[51],"TTS":[54],"built":[56],"on":[57,157],"Llasa.":[58],"Specifically,":[59],"to":[60,82,91,111,119,166],"accelerate":[61,167],"generation":[63,124,151],"process,":[64],"two":[67],"plug-and-play":[68],"Multi-Token":[69],"Prediction":[70],"(MTP)":[71],"modules":[72,78],"following":[73],"frozen":[75,109],"backbone.":[76],"These":[77],"allow":[79],"predict":[83],"multiple":[84],"tokens":[85],"one":[87],"AR":[88],"step.":[89],"Additionally,":[90],"mitigate":[92],"potential":[93],"error":[94],"propagation":[95],"caused":[96],"by":[97],"inaccurate":[98],"MTP,":[99],"design":[101,128],"a":[102,129,145],"novel":[103],"verification":[104],"algorithm":[105],"that":[106,132,142],"leverages":[107],"backbone":[110],"validate":[112],"generated":[114],"tokens,":[115],"thus":[116],"allowing":[117],"Llasa+":[118,143],"achieve":[120],"speedup":[121,148],"without":[122,149],"sacrificing":[123,150],"quality.":[125],"Furthermore,":[126],"causal":[130],"decoder":[131],"enables":[133],"speech":[135],"reconstruction":[136],"from":[137],"tokens.":[138],"Extensive":[139],"experiments":[140],"show":[141],"achieves":[144],"$1.48":[146],"\\times$":[147],"quality,":[152],"despite":[153],"being":[154],"trained":[155],"only":[156],"LibriTTS.":[158],"Moreover,":[159],"MTP-and-verification":[161],"framework":[162],"can":[163],"be":[164],"applied":[165],"any":[168],"LLM-based":[169],"model.":[170],"All":[171],"codes":[172],"models":[174],"are":[175],"publicly":[176],"available":[177],"at":[178],"https://github.com/ASLP-lab/LLaSA_Plus.":[179]},"counts_by_year":[],"updated_date":"2026-04-19T08:26:33.389920","created_date":"2026-04-03T00:00:00"}