{"id":"https://openalex.org/W4412171133","doi":"https://doi.org/10.1109/jstsp.2025.3588378","title":"AlignFormer: Modality Matching Can Achieve Better Zero-Shot Instruction-Following Speech-LLM","display_name":"AlignFormer: Modality Matching Can Achieve Better Zero-Shot Instruction-Following Speech-LLM","publication_year":2025,"publication_date":"2025-07-10","ids":{"openalex":"https://openalex.org/W4412171133","doi":"https://doi.org/10.1109/jstsp.2025.3588378"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2025.3588378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3588378","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5080637906","display_name":"Ruchao Fan","orcid":"https://orcid.org/0000-0001-5021-2747"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ruchao Fan","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012580940","display_name":"Bo Ren","orcid":"https://orcid.org/0000-0002-3534-7528"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Ren","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101942107","display_name":"Yuxuan Hu","orcid":"https://orcid.org/0000-0002-3345-7766"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxuan Hu","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987526","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-9699-9984"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-0785-8882"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5080637906"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":7.2362,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9671297,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"19","issue":"7","first_page":"1329","last_page":"1337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.994700014591217,"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":0.994700014591217,"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":0.9671000242233276,"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":0.9168999791145325,"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":0.6378718614578247},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6138337254524231},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5636296272277832},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5455800890922546},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5138457417488098},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4871918559074402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.453086256980896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3208886384963989},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2506142854690552},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15446728467941284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6378718614578247},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6138337254524231},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5636296272277832},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5455800890922546},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5138457417488098},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4871918559074402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453086256980896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3208886384963989},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2506142854690552},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15446728467941284},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2025.3588378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3588378","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W3035390927","https://openalex.org/W3097777922","https://openalex.org/W3129831491","https://openalex.org/W3153583341","https://openalex.org/W3162431424","https://openalex.org/W3205644108","https://openalex.org/W4226120743","https://openalex.org/W4283834483","https://openalex.org/W4361990931","https://openalex.org/W4385572634","https://openalex.org/W4389524500","https://openalex.org/W4391021666","https://openalex.org/W4391759660","https://openalex.org/W4392903956","https://openalex.org/W4392979802","https://openalex.org/W4401042284","https://openalex.org/W4402111222","https://openalex.org/W4404781855","https://openalex.org/W4406461912","https://openalex.org/W4408353525","https://openalex.org/W4408354168","https://openalex.org/W4411119438","https://openalex.org/W4415433622"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W4411535265","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966"],"abstract_inverted_index":{"Integrating":[0],"speech":[1,18,32,47,127,131,155,257],"into":[2],"LLM":[3,21,89,148,264],"(speech-LLM)":[4],"has":[5],"gaining":[6],"increased":[7],"attention":[8],"recently.":[9],"The":[10,88,219],"mainstream":[11],"solution":[12],"is":[13,91,250],"to":[14,41,60,95,167,235],"connect":[15],"a":[16,23,55,175,223,251],"well-trained":[17],"encoder":[19],"and":[20,33,48,73,121,130,173,200,230,258],"with":[22,107,139,152,227,242],"neural":[24,57],"adapter.":[25],"However,":[26],"the":[27,31,46,62,66,78,82,101,111,115,122,147,154,159,162,179,187,194,255,263],"length":[28,63],"mismatch":[29],"between":[30,45,65],"text":[34,98,259],"sequences":[35],"are":[36],"not":[37],"well":[38],"handled,":[39],"leading":[40],"imperfect":[42],"modality":[43,260],"matching":[44,261],"text.":[49],"In":[50,136,182],"this":[51,248],"work,":[52],"we":[53,165,184],"propose":[54,166],"novel":[56],"adapter,":[58],"AlignFormer,":[59],"reduce":[61],"gap":[64],"two":[67],"modalities.":[68],"AlignFormer":[69,113,140,220],"consists":[70],"of":[71,161,198],"CTC":[72,79],"dynamic-window":[74],"QFormer":[75],"layers,":[76],"where":[77],"alignment":[80],"provides":[81],"dynamic":[83],"window":[84],"information":[85],"for":[86,119,178],"QFormer.":[87],"backbone":[90,149],"frozen":[92],"in":[93,153,190,262],"training":[94,106,191,212,229],"preserve":[96],"its":[97],"capability,":[99],"especially":[100],"instruction":[102,116,169,195],"following":[103,117,170,196],"capability.":[104],"When":[105],"ASR":[108],"data":[109,241],"only,":[110],"proposed":[112],"unlocks":[114],"capability":[118,197],"speech-LLM":[120,138,199],"model":[123],"can":[124,141,150,221],"perform":[125,143],"zero-shot":[126],"translation":[128],"(ST)":[129],"question":[132],"answering":[133],"(SQA)":[134],"tasks.":[135],"fact,":[137],"theoretically":[142],"any":[144],"tasks":[145],"that":[146,186,210,247],"deal":[151],"version.":[156],"To":[157],"evaluate":[158],"effectiveness":[160],"instruction-following":[163],"speech-LLM,":[164],"use":[168],"rate":[171],"(IFR)":[172],"offer":[174],"systematic":[176],"perspective":[177],"IFR":[180,215,226,237],"evaluation.":[181],"addition,":[183],"find":[185],"audio":[188],"position":[189],"would":[192],"affect":[193],"conduct":[201],"an":[202],"in-depth":[203],"study":[204,249],"on":[205,238],"it.":[206],"Our":[207],"findings":[208],"show":[209],"audio-first":[211,228],"achieves":[213],"higher":[214],"than":[216],"instruction-first":[217,243],"training.":[218,244],"achieve":[222],"near":[224],"100%":[225],"game-changing":[231],"improvements":[232],"from":[233],"zero":[234],"non-zero":[236],"some":[239],"evaluation":[240],"We":[245],"believe":[246],"big":[252],"step":[253],"towards":[254],"perfect":[256],"embedding":[265],"space.":[266]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}