{"id":"https://openalex.org/W7225620152","doi":"https://doi.org/10.5281/zenodo.24094564","title":"Who Needs STT or TTS? The Waveform Remembers: Audio Memory for Voice Agents","display_name":"Who Needs STT or TTS? The Waveform Remembers: Audio Memory for Voice Agents","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225620152","doi":"https://doi.org/10.5281/zenodo.24094564"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24094564","doi":"https://doi.org/10.5281/zenodo.24094564","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24094564","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":"article-journal"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24094564","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123271472","display_name":"Vincent Marquez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Marquez, Vincent","raw_affiliation_strings":["Independent"],"raw_orcid":"https://orcid.org/0009-0003-5385-056X","affiliations":[{"raw_affiliation_string":"Independent","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5123271472"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12031","display_name":"Speech and dialogue systems","score":0.7651000022888184,"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/T12031","display_name":"Speech and dialogue systems","score":0.7651000022888184,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.2190999984741211,"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":0.00279999990016222,"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/voice-assistants","display_name":"voice assistants","score":0.7480000257492065},{"id":"https://openalex.org/keywords/audio-retrieval","display_name":"audio retrieval","score":0.6309999823570251},{"id":"https://openalex.org/keywords/audio-embeddings","display_name":"audio embeddings","score":0.7210000157356262},{"id":"https://openalex.org/keywords/speech-to-text","display_name":"speech-to-text","score":0.4169999957084656},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.9890000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7785000205039978},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6037999987602234},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5565000176429749},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.49959999322891235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4059000015258789},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.3361999988555908},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C2776728590","wikidata":"https://www.wikidata.org/wiki/Q363948","display_name":"Contradiction","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24094564","doi":"https://doi.org/10.5281/zenodo.24094564","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24094564","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":"article-journal"},{"id":"doi:10.5281/zenodo.24094565","doi":"https://doi.org/10.5281/zenodo.24094565","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24094565","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":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24094564","doi":"https://doi.org/10.5281/zenodo.24094564","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24094564","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":"article-journal"},"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/W7223789640","https://openalex.org/W7206186710","https://openalex.org/W7223324816","https://openalex.org/W7214748679","https://openalex.org/W7220926116","https://openalex.org/W7204606869","https://openalex.org/W7088010517","https://openalex.org/W4412888357","https://openalex.org/W4416370948","https://openalex.org/W7223429642"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"audio":[4,29,37,163],"memory":[5],"architecture":[6,22,195],"for":[7],"a":[8,39,67,74,81,92,100,144,168],"voice":[9,114,177],"assistant":[10],"whose":[11],"persistent":[12],"conversational":[13],"history":[14],"is":[15,80],"managed":[16],"outside":[17],"the":[18,50,77,112,122,126,152,176,185,193],"response":[19,189],"model.":[20,42],"The":[21,180],"retains":[23],"source":[24],"recordings,":[25,124],"indexes":[26],"them":[27],"with":[28,47,111],"embeddings,":[30],"retrieves":[31],"relevant":[32],"episodes,":[33],"and":[34,60,107,130,188,191],"supplies":[35],"original":[36],"to":[38,161],"compatible":[40],"answering":[41],"It":[43],"extends":[44],"this":[45],"foundation":[46],"storage":[48],"of":[49,63,86,141,148,184],"assistant's":[51],"own":[52],"speech,":[53],"anticipatory":[54],"retrieval,":[55],"background":[56],"consolidation,":[57],"contradiction":[58],"review,":[59,106],"optional":[61],"transfer":[62],"stable":[64],"experience":[65],"into":[66],"trainable":[68],"local":[69,101],"adapter.":[70],"These":[71],"extensions":[72],"form":[73],"design":[75],"proposal;":[76],"empirical":[78],"contribution":[79],"narrower":[82],"end-to-end":[83],"API":[84],"proof":[85],"concept.":[87],"On":[88],"9":[89],"November":[90],"2026,":[91],"prerecorded":[93],"synthetic-audio":[94],"experiment":[95,181],"combined":[96],"Gemini":[97,104],"Embedding":[98],"2,":[99],"SQLite":[102],"store,":[103],"audio-pair":[105],"xAI":[108],"spoken":[109,132],"responses":[110],"Ara":[113],"requested.":[115],"All":[116],"six":[117,142],"fresh":[118],"final":[119],"cases":[120],"retrieved":[121],"required":[123],"produced":[125],"intended":[127],"review":[128,171],"decisions,":[129],"generated":[131],"outputs.":[133],"A":[134],"frozen":[135],"lexical":[136],"answer":[137,154],"check":[138],"passed":[139],"five":[140],"cases;":[143],"separate":[145],"posthoc":[146],"inspection":[147],"diagnostic":[149],"transcripts":[150],"found":[151],"expected":[153],"content":[155],"in":[156],"all":[157],"six.":[158],"Mean":[159],"time":[160],"first":[162],"was":[164],"10.704":[165],"seconds,":[166],"including":[167],"7.205-second":[169],"blocking":[170],"that":[172],"did":[173],"not":[174],"influence":[175],"model's":[178],"evidence.":[179],"establishes":[182],"feasibility":[183],"recorded-audio":[186],"retrieval":[187],"path":[190],"supports":[192],"broader":[194],"proposed":[196],"here.":[197]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}
