AV-Dialog: Spoken Dialogue Models with Audio-Visual Input

• URL: http://arxiv.org/abs/2511.11124v1
• Date: Fri, 14 Nov 2025 09:56:26 GMT
• Title: AV-Dialog: Spoken Dialogue Models with Audio-Visual Input
• Authors: Tuochao Chen, Bandhav Veluri, Hongyu Gong, Shyamnath Gollakota,
• Abstract summary: We present AV-Dialog, the first framework that uses both audio and visual cues to track the target speaker, predict turn-taking, and generate coherent responses.<n>Experiments show that AV-Dialog outperforms audio-only models under interference, reducing transcription errors, improving turn-taking prediction, and enhancing human-rated dialogue quality.<n>These results highlight the power of seeing as well as hearing for speaker-aware interaction, paving the way for spoken dialogue agents that perform robustly in real-world, noisy environments.
• Score: 16.289812372606168
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dialogue models falter in noisy, multi-speaker environments, often producing irrelevant responses and awkward turn-taking. We present AV-Dialog, the first multimodal dialog framework that uses both audio and visual cues to track the target speaker, predict turn-taking, and generate coherent responses. By combining acoustic tokenization with multi-task, multi-stage training on monadic, synthetic, and real audio-visual dialogue datasets, AV-Dialog achieves robust streaming transcription, semantically grounded turn-boundary detection and accurate responses, resulting in a natural conversational flow. Experiments show that AV-Dialog outperforms audio-only models under interference, reducing transcription errors, improving turn-taking prediction, and enhancing human-rated dialogue quality. These results highlight the power of seeing as well as hearing for speaker-aware interaction, paving the way for {spoken} dialogue agents that perform {robustly} in real-world, noisy environments.

Related papers

• Covo-Audio Technical Report [61.09708870154148]
  Covo-Audio, a 7B-end LALM, directly processes continuous audio inputs and generates audio outputs within a single unified architecture.<n>Covo-Audio-Chat, a dialogue-oriented variant, demonstrates semantic strong spoken conversational abilities.
  arXiv  Detail & Related papers  (2026-02-10T14:31:11Z)
• Audio MultiChallenge: A Multi-Turn Evaluation of Spoken Dialogue Systems on Natural Human Interaction [12.216811577733125]
  We introduce Audio MultiChallenge, an open-source benchmark to evaluate E2E spoken dialogue systems under natural multi-turn interaction patterns.<n>We introduce a new axis Voice Editing that tests robustness to mid-utterance speech repairs and backtracking.<n>We curate 452 conversations from 47 speakers with 1,712 instance-specific rubrics through a hybrid audio-native agentic and human-in-the-loop pipeline.
  arXiv  Detail & Related papers  (2025-12-16T19:26:44Z)
• ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching [22.477986192421767]
  We introduce ZipVoice-Dialog, a non-autoregressive spoken dialogue generation model built upon flow matching.<n>Key designs include speaker-turn embeddings for precise speaker turn-taking.<n>We curated OpenDialog, a 6.8k-hour spoken dialogue dataset from in-the-wild speech data.
  arXiv  Detail & Related papers  (2025-07-12T15:18:47Z)
• Aligning Spoken Dialogue Models from User Interactions [55.192134724622235]
  We propose a novel preference alignment framework to improve spoken dialogue models on realtime conversations from user interactions.<n>We create a dataset of more than 150,000 preference pairs from raw multi-turn speech conversations annotated with AI feedback.<n>Our findings shed light on the importance of a well-calibrated balance among various dynamics, crucial for natural real-time speech dialogue systems.
  arXiv  Detail & Related papers  (2025-06-26T16:45:20Z)
• CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching [78.01028753403575]
  CoVoMix2 is a framework for zero-shot multi-talker dialogue generation.<n>It predicts mel-spectrograms from multi-stream transcriptions using a flow-matching-based generative model.<n>Our approach achieves state-of-the-art performance, outperforming strong baselines like MoonCast and Sesame in speech quality, speaker consistency, and inference speed.
  arXiv  Detail & Related papers  (2025-06-01T07:51:45Z)
• Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation [55.043492250775294]
  We introduce a novel Face-to-Face spoken dialogue model. It processes audio-visual speech from user input and generates audio-visual speech as the response. We also introduce MultiDialog, the first large-scale multimodal spoken dialogue corpus.
  arXiv  Detail & Related papers  (2024-06-12T04:48:36Z)
• Multimodal Contextual Dialogue Breakdown Detection for Conversational AI Models [1.4199474167684119]
  We introduce a Multimodal Contextual Dialogue Breakdown (MultConDB) model. This model significantly outperforms other known best models by achieving an F1 of 69.27.
  arXiv  Detail & Related papers  (2024-04-11T23:09:18Z)
• Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion [89.01668641930206]
  We present a framework for modeling interactional communication in dyadic conversations. We autoregressively output multiple possibilities of corresponding listener motion. Our method organically captures the multimodal and non-deterministic nature of nonverbal dyadic interactions.
  arXiv  Detail & Related papers  (2022-04-18T17:58:04Z)
• A Speaker-aware Parallel Hierarchical Attentive Encoder-Decoder Model for Multi-turn Dialogue Generation [13.820298189734686]
  This paper presents a novel open-domain dialogue generation model emphasizing the differentiation of speakers in multi-turn conversations. Our empirical results show that PHAED outperforms the state-of-the-art in both automatic and human evaluations.
  arXiv  Detail & Related papers  (2021-10-13T16:08:29Z)
• Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehension [43.352833140317486]
  Multi-party multi-turn dialogue comprehension brings unprecedented challenges. Most existing methods deal with dialogue contexts as plain texts. We propose an enhanced speaker-aware model with masking attention and heterogeneous graph networks.
  arXiv  Detail & Related papers  (2021-09-09T07:12:22Z)
• Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue [76.88174667929665]
  A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. In the existing retrieval-based multi-turn dialogue modeling, the pre-trained language models (PrLMs) as encoder represent the dialogues coarsely. We propose a novel model to fill such a gap by modeling the effective utterance-aware and speaker-aware representations entailed in a dialogue history.
  arXiv  Detail & Related papers  (2020-09-14T15:07:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.