Metraipolis › archive › dc_74d7fd9ef475
PERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken Dialogue — arXiv:2610.07725
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07725
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:19:03.336Z
- SHA-256 of the archived text
bd2c37d6cc449bb1d50554b15b1553a1c0a8c91a15b24a0e64f323dc09de7ddf- Stable URL of this page
https://metraipolis.com/documento/dc_74d7fd9ef475
How to cite
PERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken Dialogue — arXiv:2610.07725 — arXiv (en), https://arxiv.org/abs/2610.07725 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_74d7fd9ef475 (Metraipolis archive dc_74d7fd9ef475, sha256 bd2c37d6cc449bb1d50554b15b1553a1c0a8c91a15b24a0e64f323dc09de7ddf)
BibTeX
@misc{dc74d7fd9ef475,
title = {PERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken Dialogue — arXiv:2610.07725},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07725},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_74d7fd9ef475; sha256 bd2c37d6cc449bb1d50554b15b1553a1c0a8c91a15b24a0e64f323dc09de7ddf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07725. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern voice assistants may be shared by multiple users and should be able to answer questions about earlier conversations such as "When did I originally plan to leave?" or adapt their behavior to individual users based on past interactions. This requires more than retrieving a topically similar passage: the assistant must identify the current speaker, recover the relevant past state, and distinguish it from later revisions. We present PERSIST, a persistent memory system for multi-session, multi-speaker spoken dialogue that explicitly models Who, What, and When. PERSIST structures cross-session histories into readable event records and retrieves them with a 3W joint scoring mechanism that combines semantic content, acoustic speaker identity, and temporal state. For real-time full-duplex interaction, PERSIST further reuses intermediate representations from the dialogue backbone, avoiding query-audio re-encoding and reducing retrieval latency from 578.42 ms to 7.03 ms. We also introduce SpokenTrace, a diagnostic benchmark that factorizes evaluation along memory tasks and speaker-query types, exposing failures in recall, speaker attribution, and temporal-state tracking. On SpokenTrace, PERSIST achieves 85.08% end-to-end task accuracy and improves all-support EM@3 from 49.01% with BGE-large to 82.10%. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.07725 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:15:24.547Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).