Metraipolis › archive › dc_cc17930aa42f

DUPAR: Dual-Path Conversational Retrieval via Speech Retriever with Cross-Turn Evidence Caching — arXiv:2609.18042

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18042
License (as archived)
CC0-1.0
Archived
2026-10-15T16:15:58.784Z
SHA-256 of the archived text
ab62648e6ff85506895caaabfb7c3563c0bbae7a1e25a59f6a31d6714d2d936b
Stable URL of this page
https://metraipolis.com/documento/dc_cc17930aa42f

How to cite

DUPAR: Dual-Path Conversational Retrieval via Speech Retriever with Cross-Turn Evidence Caching — arXiv:2609.18042 — arXiv (en), https://arxiv.org/abs/2609.18042 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc17930aa42f (Metraipolis archive dc_cc17930aa42f, sha256 ab62648e6ff85506895caaabfb7c3563c0bbae7a1e25a59f6a31d6714d2d936b)
BibTeX
@misc{dccc17930aa42f,
  title = {DUPAR: Dual-Path Conversational Retrieval via Speech Retriever with Cross-Turn Evidence Caching — arXiv:2609.18042},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18042},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc17930aa42f; sha256 ab62648e6ff85506895caaabfb7c3563c0bbae7a1e25a59f6a31d6714d2d936b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18042. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Voice assistants grounded in external knowledge typically use automatic speech recognition (ASR) to transcribe speech queries before retrieving evidence from textual knowledge bases. This cascade adds latency and propagates recognition errors, whereas direct speech retrieval is vulnerable to cross-modal misalignment. To address these limitations, we propose DUPAR, a conversational retrieval framework with complementary slow and fast paths. The fast path uses a task-adapted audio encoder aligned with frozen BGE-M3 text embeddings to search a cross-turn evidence cache. When cache confidence is insufficient, the slow path fuses full-index retrieval using audio and ASR-transcript embeddings, and the selected evidence refreshes the next-turn evidence cache through one-hop graph expansion. On a domain-specific knowledge base, our trained audio encoder approaches text-retrieval accuracy on clean speech with a 3.75$\times$ query-side speedup over ASR + Text Encoder. It raises average Recall@10 from 0.771 to 0.875 on the noise benchmark and improves overall Recall@1 by 4.2 percentage points across synthesized speaking styles. Compared with full-index audio retrieval, cross-turn evidence caching significantly reduces retrieval errors when the previous turn retrieves correct evidence and the follow-up targets a one-hop neighboring chunk.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.18042 — 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 2026-10-15T15:44:55.715Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).