{"id":"https://openalex.org/W4392931626","doi":"https://doi.org/10.1109/icassp48485.2024.10445874","title":"Connecting Speech Encoder and Large Language Model for ASR","display_name":"Connecting Speech Encoder and Large Language Model for ASR","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931626","doi":"https://doi.org/10.1109/icassp48485.2024.10445874"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5109693003","display_name":"Wenyi Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenyi Yu","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering","Department of Electronic Engineering, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039664887","display_name":"Changli Tang","orcid":"https://orcid.org/0000-0002-6550-1901"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changli Tang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering","Department of Electronic Engineering, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007755497","display_name":"Guangzhi Sun","orcid":"https://orcid.org/0000-0003-3190-497X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhi Sun","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering","Department of Electronic Engineering, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692700","display_name":"Xianzhao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianzhao Chen","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101667381","display_name":"Tian Tan","orcid":"https://orcid.org/0000-0002-4723-0044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Tan","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318020","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-7824-4839"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366029","display_name":"Lu Lu","orcid":"https://orcid.org/0000-0002-5476-5768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Lu","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101108160","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering","Department of Electronic Engineering, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5109693003"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":12.9324,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.98973998,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"12637","last_page":"12641"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9955999851226807,"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/T10028","display_name":"Topic Modeling","score":0.9941999912261963,"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/encoder","display_name":"Encoder","score":0.7011548280715942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6254832148551941},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6089425086975098},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5543637275695801},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43945226073265076},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4337102174758911},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4298448860645294},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2295595109462738},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11874628067016602}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7011548280715942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6254832148551941},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6089425086975098},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5543637275695801},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43945226073265076},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4337102174758911},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4298448860645294},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2295595109462738},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11874628067016602},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":50,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W3198694222","https://openalex.org/W3209059054","https://openalex.org/W4226033575","https://openalex.org/W4322718191","https://openalex.org/W4323066695","https://openalex.org/W4361866031","https://openalex.org/W4366850747","https://openalex.org/W4375958083","https://openalex.org/W4376312115","https://openalex.org/W4377130946","https://openalex.org/W4378174011","https://openalex.org/W4378711593","https://openalex.org/W4380994269","https://openalex.org/W4381827575","https://openalex.org/W4383989131","https://openalex.org/W4385807435","https://openalex.org/W4386351448","https://openalex.org/W4389519587","https://openalex.org/W4389524500","https://openalex.org/W4391021457","https://openalex.org/W4391021666","https://openalex.org/W4392903956","https://openalex.org/W4392908891","https://openalex.org/W4392909390","https://openalex.org/W4393178509","https://openalex.org/W4402671548","https://openalex.org/W6771467084","https://openalex.org/W6778883912","https://openalex.org/W6794212170","https://openalex.org/W6810334672","https://openalex.org/W6847363464","https://openalex.org/W6849177959","https://openalex.org/W6850218400","https://openalex.org/W6850625674","https://openalex.org/W6851513886","https://openalex.org/W6851950068","https://openalex.org/W6852326057","https://openalex.org/W6852447913","https://openalex.org/W6852800892","https://openalex.org/W6853089504","https://openalex.org/W6853094705","https://openalex.org/W6853116092","https://openalex.org/W6853249747","https://openalex.org/W6853515732","https://openalex.org/W6853998256","https://openalex.org/W6854445763","https://openalex.org/W6855414158","https://openalex.org/W6855793536","https://openalex.org/W6855801281"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2944691285","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"The":[0],"impressive":[1],"capability":[2],"and":[3,56,90,100],"versatility":[4],"of":[5,43,167],"large":[6],"language":[7],"models":[8,28],"(LLMs)":[9],"have":[10],"aroused":[11],"increasing":[12],"attention":[13],"in":[14,172],"automatic":[15],"speech":[16,32,159,183],"recognition":[17],"(ASR),":[18],"with":[19,34,74,96,109,161],"several":[20],"pioneering":[21],"studies":[22],"attempting":[23],"to":[24,118,154,157],"build":[25],"integrated":[26],"ASR":[27,130],"by":[29],"connecting":[30],"a":[31,40,148,162],"encoder":[33],"an":[35],"LLM.":[36],"This":[37],"paper":[38],"presents":[39],"comparative":[41],"study":[42],"three":[44],"commonly":[45,85],"used":[46,86],"structures":[47,180],"as":[48,65,67],"connectors,":[49],"including":[50],"fully":[51],"connected":[52],"layers,":[53],"multi-head":[54],"cross-attention,":[55],"Q-Former.":[57],"Speech":[58],"encoders":[59],"from":[60,69,145],"the":[61,70,84,94,127,135,165,168],"Whisper":[62,128],"model":[63,72,76,131],"series":[64,73],"well":[66,117],"LLMs":[68,95,108,114,156],"Vicuna":[71],"different":[75],"sizes":[77],"were":[78,81,132],"studied.":[79],"Experiments":[80],"performed":[82],"on":[83,134,181],"LibriSpeech,":[87],"Common":[88],"Voice,":[89],"GigaSpeech":[91],"datasets,":[92,120],"where":[93,121],"Q-Formers":[97],"demonstrated":[98],"consistent":[99],"considerable":[101],"word":[102],"error":[103],"rate":[104],"(WER)":[105],"reductions":[106,125,176],"over":[107,126,177],"other":[110,178],"connector":[111,179],"structures.":[112],"Q-Former-based":[113],"can":[115],"generalise":[116],"out-of-domain":[119],"12%":[122],"relative":[123,174],"WER":[124,175],"baseline":[129],"achieved":[133],"Eval2000":[136],"test":[137],"set":[138],"without":[139],"using":[140],"any":[141],"in-domain":[142],"training":[143],"data":[144],"Switchboard.":[146],"Moreover,":[147],"novel":[149],"segment-level":[150],"Q-Former":[151],"is":[152],"proposed":[153],"enable":[155],"recognise":[158],"segments":[160],"duration":[163],"exceeding":[164],"limitation":[166],"encoders,":[169],"which":[170],"results":[171],"17%":[173],"90-second-long":[182],"data.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":7}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}