OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions

• URL: http://arxiv.org/abs/2505.21724v1
• Date: Tue, 27 May 2025 20:12:46 GMT
• Title: OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions
• Authors: Cheng Luo, Jianghui Wang, Bing Li, Siyang Song, Bernard Ghanem,
• Abstract summary: We introduce Online Multimodal Conversational Response Generation (OMCRG), a novel task that aims to online generate synchronized verbal and non-verbal listener feedback.<n>We propose OmniResponse, a Multimodal Large Language Model (MLLM) that autoregressively generates high-quality multi-modal listener responses.<n>We present ResponseNet, a new dataset comprising 696 high-quality dyadic interactions featuring synchronized split-screen videos, multichannel audio, transcripts, and facial behavior annotations.
• Score: 50.705439960008235
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this paper, we introduce Online Multimodal Conversational Response Generation (OMCRG), a novel task that aims to online generate synchronized verbal and non-verbal listener feedback, conditioned on the speaker's multimodal input. OMCRG reflects natural dyadic interactions and poses new challenges in achieving synchronization between the generated audio and facial responses of the listener. To address these challenges, we innovatively introduce text as an intermediate modality to bridge the audio and facial responses. We hence propose OmniResponse, a Multimodal Large Language Model (MLLM) that autoregressively generates high-quality multi-modal listener responses. OmniResponse leverages a pretrained LLM enhanced with two novel components: Chrono-Text, which temporally anchors generated text tokens, and TempoVoice, a controllable online TTS module that produces speech synchronized with facial reactions. To support further OMCRG research, we present ResponseNet, a new dataset comprising 696 high-quality dyadic interactions featuring synchronized split-screen videos, multichannel audio, transcripts, and facial behavior annotations. Comprehensive evaluations conducted on ResponseNet demonstrate that OmniResponse significantly outperforms baseline models in terms of semantic speech content, audio-visual synchronization, and generation quality.

Related papers

• CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching [79.0241611035794]
  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)
• Beyond Words: Multimodal LLM Knows When to Speak [25.374878759869333]
  We focus on real-time prediction of response types, with an emphasis on short, reactive utterances that depend on subtle, multimodal signals across vision, audio, and text.<n>We introduce a new multimodal dataset constructed from real-world conversational videos, containing temporally aligned visual, auditory, and textual streams.<n>We propose MM-When2Speak, a multimodal LLM-based model that adaptively integrates visual, auditory, and textual context to predict when a response should occur, and what type of response is appropriate.
  arXiv  Detail & Related papers  (2025-05-20T17:42:34Z)
• OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication [19.688375369516923]
  We introduce an end-to-end unified framework that simultaneously generates synchronized speech and talking head videos from text and reference video in real-time zero-shot scenarios.<n>Our method surpasses existing approaches in generation quality, particularly excelling in style preservation and audio-video synchronization.
  arXiv  Detail & Related papers  (2025-04-03T09:48:13Z)
• SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation [17.56310064245171]
  SALMON-omni is a speech understanding and generation model capable of simultaneously listening to its own generated speech sounds while speaking.<n> SALMON-omni excels at managing turn-taking, barge-in, and echo cancellation scenarios, establishing its potential as a robust prototype for full- conversational AI systems.
  arXiv  Detail & Related papers  (2024-11-27T08:38:57Z)
• OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation [53.7173034249361]
  End-to-end GPT-based model OmniFlatten capable of effectively modeling complex behaviors inherent natural conversations with low latency.<n>Our approach offers a simple modeling technique and a promising research direction for developing efficient and natural end-to-end full- spoken dialogue systems.
  arXiv  Detail & Related papers  (2024-10-23T11:58:58Z)
• IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities [55.11130688075417]
  We introduce IntrinsicVoic,e an LLM designed with intrinsic real-time voice interaction capabilities. Our novelty architecture, GroupFormer, can reduce speech sequences to lengths comparable to text sequences. We construct a multi-turn speech-to-speech dialogue dataset named method-500k which includes nearly 500k turns of speech-to-speech dialogues.
  arXiv  Detail & Related papers  (2024-10-09T05:04:31Z)
• PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems [7.326036800127981]
  Multimodal language models that process both text and speech have a potential for applications in spoken dialogue systems. generating a spoken response requires the prior generation of a written response, and speech sequences are significantly longer than text sequences. This study addresses these issues by extending the input and output sequences of the language model to support the parallel generation of text and speech.
  arXiv  Detail & Related papers  (2024-06-18T09:23:54Z)
• A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation [48.84039953531355]
  We propose a novel non-autoregressive generation framework for simultaneous speech translation (NAST-S2X) NAST-S2X integrates speech-to-text and speech-to-speech tasks into a unified end-to-end framework. It achieves high-quality simultaneous interpretation within a delay of less than 3 seconds and provides a 28 times decoding speedup in offline generation.
  arXiv  Detail & Related papers  (2024-06-11T04:25:48Z)
• HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations [76.64792382097724]
  We present HeterMPC, a graph-based neural network for response generation in multi-party conversations (MPCs) HeterMPC models the semantics of utterances and interlocutors simultaneously with two types of nodes in a graph. Through multi-hop updating, HeterMPC can adequately utilize the structural knowledge of conversations for response generation.
  arXiv  Detail & Related papers  (2022-03-16T09:50:32Z)
• Responsive Listening Head Generation: A Benchmark Dataset and Baseline [58.168958284290156]
  We define the responsive listening head generation task as the synthesis of a non-verbal head with motions and expressions reacting to the multiple inputs. Unlike speech-driven gesture or talking head generation, we introduce more modals in this task, hoping to benefit several research fields.
  arXiv  Detail & Related papers  (2021-12-27T07:18:50Z)

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.