Metraipolis › archive › dc_50fd9742e524
S2Dialog: Multimodal Dialogue Retrieval with Semantic and Acoustic-Style Modeling — arXiv:2608.14029
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14029
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:27:54.730Z
- SHA-256 of the archived text
22c1819b4a712746e9f047a07fa8f27491f3f3e46679935a5170e035a687b264- Stable URL of this page
https://metraipolis.com/documento/dc_50fd9742e524
How to cite
S2Dialog: Multimodal Dialogue Retrieval with Semantic and Acoustic-Style Modeling — arXiv:2608.14029 — arXiv (en), https://arxiv.org/abs/2608.14029 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_50fd9742e524 (Metraipolis archive dc_50fd9742e524, sha256 22c1819b4a712746e9f047a07fa8f27491f3f3e46679935a5170e035a687b264)
BibTeX
@misc{dc50fd9742e524,
title = {S2Dialog: Multimodal Dialogue Retrieval with Semantic and Acoustic-Style Modeling — arXiv:2608.14029},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14029},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_50fd9742e524; sha256 22c1819b4a712746e9f047a07fa8f27491f3f3e46679935a5170e035a687b264},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14029. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal dialogue retrieval aims to retrieve dialogues from multimodal dialogue banks that are similar to a target dialogue in terms of both textual semantics and acoustic conversational styles. Such dialogue-level retrieval is crucial for many dialogue-related tasks, including Emotion Recognition in Conversation, Spoken Dialogue Systems, and Conversational Speech Synthesis, where external dialogue examples can provide valuable semantic and stylistic references. However, existing retrieval methods are still largely limited to utterance-level or unimodal matching, and often fail to capture the global semantic coherence and stylistic consistency of an entire dialogue. To address this gap, we propose S2Dialog, a unified framework for dialogue-level semantic-style retrieval from multimodal dialogue banks. Specifically, S2Dialog consists of a Dialogue-level Textual Retriever and a Dialogue-level Acoustic Retriever, which encode the textual and acoustic modalities of a dialogue into dialogue-level representations, respectively. To further enhance multimodal retrieval, we introduce Dialogue-level Textual-Acoustic Contrastive Learning, which aligns semantically and stylistically similar dialogues while distinguishing unrelated ones. Extensive experiments on the multimodal dialogue dataset DailyTalk demonstrate that S2Dialog achieves outstanding retrieval performance. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.14029 — 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 2026-10-19T02:20:31.904Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).