{"id":"https://openalex.org/W7214224823","doi":"https://doi.org/10.48550/arxiv.2609.27195","title":"Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoders","display_name":"Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoders","publication_year":2026,"publication_date":"2026-09-23","ids":{"openalex":"https://openalex.org/W7214224823","doi":"https://doi.org/10.48550/arxiv.2609.27195"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.27195","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.27195","pdf_url":"https://arxiv.org/pdf/2609.27195","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.27195","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018610283","display_name":"Vsevolod Kovalev","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kovalev, Vsevolod","raw_affiliation_strings":["Boston University , Boston , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University , Boston , MA , USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075510192","display_name":"Pranay Manocha","orcid":"https://orcid.org/0000-0003-3284-5908","observed_orcids":["https://orcid.org/0000-0003-3284-5908"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manocha, Pranay","raw_affiliation_strings":["Princeton University , Princeton , NJ , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University , Princeton , NJ , USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9136000275611877,"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":0.9136000275611877,"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":0.07530000060796738,"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":0.003800000064074993,"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/speech-encoder","display_name":"speech encoder","score":0.6700000166893005},{"id":"https://openalex.org/keywords/representational-drift","display_name":"representational drift","score":0.8240000009536743},{"id":"https://openalex.org/keywords/speech-interference","display_name":"speech interference","score":0.6349999904632568},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"speaker verification","score":0.6650000214576721},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8360000252723694},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"emotion recognition","score":0.9430000185966492},{"id":"https://openalex.org/keywords/intent-recognition","display_name":"intent classification","score":0.9190000295639038},{"id":"https://openalex.org/keywords/frozen-encoder","display_name":"frozen encoder","score":0.515999972820282},{"id":"https://openalex.org/keywords/background-noise","display_name":"background noise","score":0.43700000643730164}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7379000186920166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6851999759674072},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6334999799728394},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C2777185736","wikidata":"https://www.wikidata.org/wiki/Q7265603","display_name":"QUIET","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5317999720573425},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48350000381469727},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.27195","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.27195","pdf_url":"https://arxiv.org/pdf/2609.27195","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.27195","doi":"https://doi.org/10.48550/arxiv.2609.27195","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.27195","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.27195","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.27195","pdf_url":"https://arxiv.org/pdf/2609.27195","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214224823.pdf","grobid_xml":"https://content.openalex.org/works/W7214224823.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3095406643","https://openalex.org/W2407162741","https://openalex.org/W1483322323","https://openalex.org/W4297841702","https://openalex.org/W2763487702","https://openalex.org/W87605858","https://openalex.org/W2041336666","https://openalex.org/W7202415661","https://openalex.org/W4385822644","https://openalex.org/W2514627796"],"abstract_inverted_index":{"Non-speech":[0],"interference":[1,64,70,91,106],"can":[2,107],"change":[3,108],"a":[4,86],"speech":[5,52,69,81,114],"representation":[6],"without":[7],"causing":[8],"comparable":[9],"task":[10,36,133],"loss.":[11,134],"We":[12],"test":[13],"eight":[14],"frozen":[15],"encoders":[16],"on":[17,75],"four":[18],"tasks,":[19],"adding":[20],"non-speech":[21],"sounds":[22],"throughout":[23],"recordings,":[24],"during":[25],"speech,":[26],"or":[27],"in":[28],"pauses.":[29],"Under":[30],"whole-recording":[31],"interference,":[32],"embedding":[33],"drift":[34,127],"tracks":[35],"loss":[37,74],"across":[38],"seven":[39],"sounds,":[40,124],"with":[41],"mean":[42],"Spearman":[43],"correlations":[44],"of":[45,122],"0.81-0.88.":[46],"Moving":[47],"the":[48,97,102,120],"same":[49],"sound":[50],"between":[51],"and":[53,80],"pauses":[54],"changes":[55,93],"this":[56],"pattern.":[57],"At":[58],"quiet":[59],"to":[60],"moderate":[61],"levels,":[62],"pause":[63],"produces":[65],"larger":[66,126],"drift,":[67],"while":[68],"usually":[71],"causes":[72],"greater":[73,132],"intent":[76],"recognition,":[77],"speaker":[78],"verification":[79],"recognition.":[82],"Emotion":[83],"recognition":[84],"shows":[85],"weaker":[87],"placement":[88],"effect.":[89],"Pause":[90],"also":[92],"speech-frame":[94],"representations":[95],"beyond":[96],"injected":[98],"region.":[99],"Even":[100],"below":[101],"estimated":[103],"recording":[104],"background,":[105],"embeddings":[109],"as":[110,112],"much":[111],"repeated":[113],"takes":[115],"do.":[116],"Drift":[117],"helps":[118],"rank":[119],"effects":[121],"different":[123],"but":[125],"does":[128],"not":[129],"consistently":[130],"indicate":[131]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-09-25T00:00:00"}
