{"id":"https://openalex.org/W4392904322","doi":"https://doi.org/10.1109/icassp48485.2024.10447746","title":"Are Soft Prompts Good Zero-Shot Learners for Speech Recognition?","display_name":"Are Soft Prompts Good Zero-Shot Learners for Speech Recognition?","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904322","doi":"https://doi.org/10.1109/icassp48485.2024.10447746"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447746","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/A5104217727","display_name":"Dianwen Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY","SG"],"is_corresponding":true,"raw_author_name":"Dianwen Ng","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393899","display_name":"Chong Zhang","orcid":"https://orcid.org/0000-0002-2162-4344"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Chong Zhang","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866147","display_name":"Ruixi Zhang","orcid":"https://orcid.org/0000-0002-0376-4327"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Ruixi Zhang","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101568886","display_name":"Yukun Ma","orcid":"https://orcid.org/0000-0002-4419-4287"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Yukun Ma","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092905575","display_name":"Fabian Ritter-Gutierrez","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fabian Ritter-Gutierrez","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562097","display_name":"Trung Hieu Nguyen","orcid":"https://orcid.org/0000-0002-2683-253X"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Trung Hieu Nguyen","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102306089","display_name":"Chongjia Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Chongjia Ni","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103758307","display_name":"Shengkui Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Shengkui Zhao","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5104217727"],"corresponding_institution_ids":["https://openalex.org/I172675005","https://openalex.org/I4210086143"],"apc_list":null,"apc_paid":null,"fwci":0.3651,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61783724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"10366","last_page":"10370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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":0.9976000189781189,"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":0.8000904321670532},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.7711246013641357},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7114626169204712},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5830626487731934},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5749383568763733},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5225793123245239},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45406433939933777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43652892112731934},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37254199385643005},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.324895441532135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000904321670532},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.7711246013641357},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7114626169204712},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5830626487731934},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5749383568763733},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5225793123245239},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45406433939933777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43652892112731934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37254199385643005},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.324895441532135},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447746","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":[{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2033875152","https://openalex.org/W3036601975","https://openalex.org/W3163142165","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205689591","https://openalex.org/W4205991051","https://openalex.org/W4319862642","https://openalex.org/W4322825254","https://openalex.org/W4372342491","https://openalex.org/W4375869257","https://openalex.org/W4377111648","https://openalex.org/W4385807453","https://openalex.org/W4385822514","https://openalex.org/W4385822786","https://openalex.org/W4401610024","https://openalex.org/W4403635980","https://openalex.org/W6780218876","https://openalex.org/W6847363464","https://openalex.org/W6849622896","https://openalex.org/W6850477478","https://openalex.org/W6852718240","https://openalex.org/W6853315073","https://openalex.org/W6859986920"],"related_works":["https://openalex.org/W107105315","https://openalex.org/W1584537303","https://openalex.org/W4388155270","https://openalex.org/W4367156293","https://openalex.org/W2750549761","https://openalex.org/W1872724644","https://openalex.org/W28826848","https://openalex.org/W2122272819","https://openalex.org/W2994151208","https://openalex.org/W2130894091"],"abstract_inverted_index":{"Large":[0],"self-supervised":[1],"pre-trained":[2],"speech":[3,66],"models":[4],"require":[5],"computationally":[6],"expensive":[7],"fine-tuning":[8],"for":[9,99],"downstream":[10],"tasks.":[11],"Soft":[12,91],"prompt":[13,24],"tuning":[14],"offers":[15],"a":[16],"simple":[17],"parameter-efficient":[18],"alternative":[19],"by":[20,57],"utilizing":[21],"minimal":[22],"soft":[23,62,108],"guidance,":[25],"enhancing":[26],"portability":[27],"while":[28,81],"also":[29,82,102],"maintaining":[30],"competitive":[31],"performance.":[32],"However,":[33],"not":[34,97],"many":[35],"people":[36],"understand":[37],"how":[38],"and":[39,112],"why":[40],"this":[41,45,54],"is":[42],"so.":[43],"In":[44],"study,":[46],"we":[47,123],"aim":[48],"to":[49,85,131,142],"deepen":[50],"our":[51],"understanding":[52],"of":[53,61,88,107,137],"emerging":[55],"method":[56],"investigating":[58],"the":[59,86],"role":[60,73],"prompts":[63,92,130],"in":[64,77],"automatic":[65],"recognition":[67],"(ASR).":[68],"Our":[69],"findings":[70],"highlight":[71],"their":[72],"as":[74],"zero-shot":[75,138],"learners":[76],"improving":[78],"ASR":[79],"performance":[80],"exposing":[83],"them":[84],"risk":[87],"malicious":[89],"modifications.":[90],"aid":[93],"generalization":[94],"but":[95],"are":[96,135],"obligatory":[98],"inference.":[100],"We":[101],"identify":[103],"two":[104],"primary":[105],"roles":[106],"prompts:":[109],"content":[110],"refinement":[111],"noise":[113,129,144],"information":[114],"enhancement,":[115],"which":[116],"enhances":[117],"robustness":[118],"against":[119],"background":[120],"noise.":[121],"Additionally,":[122],"propose":[124],"an":[125],"effective":[126],"modification":[127],"on":[128,140],"show":[132],"that":[133],"they":[134],"capable":[136],"learning":[139],"adapting":[141],"out-of-distribution":[143],"environments.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
