{"id":"https://openalex.org/W4416799863","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249036","title":"Explainable Disentanglement on Discrete Speech Representations for Noise-Robust ASR","display_name":"Explainable Disentanglement on Discrete Speech Representations for Noise-Robust ASR","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799863","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249036"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"Shreyas Gopal","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":true,"raw_author_name":"Shreyas Gopal","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ashutosh Anshul","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":"Ashutosh Anshul","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037624853","display_name":"Haoyang Li","orcid":"https://orcid.org/0000-0003-3024-1350"},"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":"Haoyang Li","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112025134","display_name":"Yue Heng Yeo","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":"Yue Heng Yeo","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091096053","display_name":"Hexin Liu","orcid":"https://orcid.org/0000-0002-3998-9229"},"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":"Hexin Liu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","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":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19131406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2535","last_page":"2540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6455000042915344,"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":0.6455000042915344,"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":0.1582999974489212,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05829999968409538,"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/interpretability","display_name":"Interpretability","score":0.8561000227928162},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6905999779701233},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3862999975681305},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3815999925136566},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.3718000054359436},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.362199991941452},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3555000126361847},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.3488999903202057}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8561000227928162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7099000215530396},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6905999779701233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6399999856948853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4480000138282776},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3555000126361847},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C2777185736","wikidata":"https://www.wikidata.org/wiki/Q7265603","display_name":"QUIET","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2603567530","https://openalex.org/W3048062783","https://openalex.org/W3197849864","https://openalex.org/W3205533980","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4312096533","https://openalex.org/W4312508181","https://openalex.org/W4372268681","https://openalex.org/W4372342491","https://openalex.org/W4385807453","https://openalex.org/W4392904154","https://openalex.org/W4402112335","https://openalex.org/W4402118927","https://openalex.org/W4402670040","https://openalex.org/W4408355053","https://openalex.org/W4410087476","https://openalex.org/W4415433242"],"related_works":[],"abstract_inverted_index":{"Discrete":[0],"audio":[1],"representations":[2],"are":[3,20,74],"gaining":[4],"traction":[5],"in":[6,49,59,114],"speech":[7,44,58,89,93],"modeling":[8],"due":[9],"to":[10,118,141],"their":[11],"interpretability":[12],"and":[13,90,102,120,144],"compatibility":[14],"with":[15],"large":[16],"language":[17],"models,":[18],"but":[19],"not":[21],"always":[22],"optimized":[23],"for":[24,37],"noisy":[25],"or":[26],"real-world":[27],"environments.":[28],"Building":[29],"on":[30,126],"existing":[31],"works":[32],"that":[33,82,95,134],"quantize":[34],"Whisper":[35,107],"embeddings":[36],"speech-to-unit":[38],"modeling,":[39],"we":[40,109],"propose":[41],"disentangling":[42],"semantic":[43],"content":[45],"from":[46],"background":[47],"noise":[48,68],"the":[50,60,127,135],"latent":[51],"space.":[52],"Our":[53],"end-to-end":[54],"model":[55],"separates":[56],"clean":[57],"form":[61],"of":[62,100],"codebook":[63],"tokens,":[64],"while":[65],"extracting":[66],"interpretable":[67],"vectors":[69],"as":[70],"quantization":[71],"residue":[72],"which":[73],"supervised":[75],"via":[76],"a":[77,97],"lightweight":[78],"classifier.":[79],"We":[80],"show":[81,110,133],"our":[83],"approach":[84],"improves":[85,103],"alignment":[86],"between":[87],"clean/noisy":[88],"text,":[91],"producing":[92],"tokens":[94],"display":[96],"high":[98],"degree":[99],"noiseinvariance,":[101],"ASR":[104],"performance.":[105],"Keeping":[106],"frozen,":[108],"an":[111],"82%":[112],"reduction":[113],"error":[115],"rate":[116],"compared":[117],"Whisper,":[119],"35%":[121],"improvement":[122],"over":[123],"baseline":[124],"methods":[125],"VBDemand":[128],"test":[129],"set.":[130],"Further":[131],"analyses":[132],"learned":[136],"token":[137],"space":[138],"generalizes":[139],"well":[140],"both":[142],"seen":[143],"unseen":[145],"acoustic":[146],"conditions.":[147]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-28T00:00:00"}