{"id":"https://openalex.org/W7225335111","doi":"https://doi.org/10.5281/zenodo.23988670","title":"Do Full-Duplex Speech Models Listen in Text? A Latent Transcript of the User and a Voice Gate That Closes It","display_name":"Do Full-Duplex Speech Models Listen in Text? A Latent Transcript of the User and a Voice Gate That Closes It","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225335111","doi":"https://doi.org/10.5281/zenodo.23988670"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23988670","doi":"https://doi.org/10.5281/zenodo.23988670","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23988670","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23988670","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160962988","display_name":"Mikhail Kulik","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kulik, Mikhail","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160962988"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.9014000296592712,"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":0.9014000296592712,"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/T12031","display_name":"Speech and dialogue systems","score":0.04639999940991402,"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":0.02879999950528145,"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/moshi","display_name":"Moshi","score":0.6340000033378601},{"id":"https://openalex.org/keywords/activation-patching","display_name":"activation patching","score":0.5559999942779541},{"id":"https://openalex.org/keywords/ablation","display_name":"ablation","score":0.460999995470047},{"id":"https://openalex.org/keywords/conversational-ai","display_name":"conversational AI","score":0.36399999260902405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6152999997138977},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5996999740600586},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5827000141143799},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.35260000824928284},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33320000767707825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3212999999523163},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.27469998598098755},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23988670","doi":"https://doi.org/10.5281/zenodo.23988670","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23988670","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23988671","doi":"https://doi.org/10.5281/zenodo.23988671","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23988671","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23988670","doi":"https://doi.org/10.5281/zenodo.23988670","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23988670","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403883071","https://openalex.org/W7213595700","https://openalex.org/W7164054370","https://openalex.org/W7212059771","https://openalex.org/W7164402690","https://openalex.org/W7223704125","https://openalex.org/W7212007012","https://openalex.org/W7221777691","https://openalex.org/W7224312081","https://openalex.org/W7222472049"],"abstract_inverted_index":{"Full-duplex":[0],"speech":[1,76,152],"models":[2],"such":[3],"as":[4,29],"Moshi":[5,37],"listen":[6],"and":[7,33,38,74,97,153,176,195,202,220],"speak":[8],"at":[9],"the":[10,26,46,51,55,79,105,126,136,146,154,166,173,189,193,196,209,211],"same":[11],"time,":[12],"but":[13,159,215],"emit":[14],"text":[15,52],"only":[16],"for":[17,63],"their":[18],"own":[19,148,156],"speech.":[20],"Do":[21],"they":[22],"nevertheless":[23],"represent":[24],"what":[25],"user":[27,47,57],"says":[28],"text?":[30],"Applying":[31],"logit":[32],"tuned":[34,108],"lenses":[35],"to":[36],"PersonaPlex,":[39],"we":[40],"find":[41],"a":[42,69,107,111,122,169],"latent":[43],"transcript":[44,118,190,212],"of":[45,65,132,135,165],"in":[48,145,172,185],"layers":[49,186],"21\u201330:":[50],"head":[53],"ranks":[54],"current":[56],"word":[58,84,112],"among":[59],"its":[60,133,206],"top":[61],"five":[62],"46\u201348%":[64],"content":[66],"words":[67,94],"above":[68],"matched":[70],"control,":[71],"on":[72,208],"read":[73],"meeting":[75],"alike,":[77],"while":[78,125],"output":[80],"stays":[81],"silent.":[82],"The":[83,138],"becomes":[85],"readable":[86,214],"about":[87],"150":[88],"ms":[89],"before":[90],"it":[91,129,181],"ends,":[92],"predictable":[93],"are":[95],"favoured,":[96],"errors":[98],"share":[99],"form":[100],"rather":[101],"than":[102,205],"meaning":[103],"with":[104],"target;":[106],"lens":[109],"finds":[110],"code":[113],"from":[114],"layer":[115],"12.":[116],"This":[117],"is":[119,140,182,200,213],"closed":[120],"by":[121,142,161],"voice":[123],"gate:":[124],"model":[127],"speaks,":[128],"loses":[130],"50\u201377%":[131],"readout":[134],"user.":[137],"gate":[139],"triggered":[141],"speech-like":[143],"audio":[144],"model's":[147,155],"channel,":[149,175],"including":[150],"time-reversed":[151],"generated":[157],"replies,":[158],"hardly":[160,216],"noise,":[162],"an":[163],"echo":[164],"user,":[167],"or":[168],"second":[170],"talker":[171],"user's":[174],"activation":[177],"patching":[178],"shows":[179],"that":[180],"set":[183],"up":[184],"1\u20138.":[187],"Ablating":[188],"barely":[191],"changes":[192],"reply,":[194],"gate's":[197],"behavioural":[198],"effect":[199,207],"weaker":[201],"less":[203],"specific":[204],"representation:":[210],"used.":[217],"Code,":[218],"notebooks":[219],"results:":[221],"https://github.com/gglenpoi/listen-in-text":[222]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-11-06T00:00:00"}