OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation

• URL: http://arxiv.org/abs/2410.17799v1
• Date: Wed, 23 Oct 2024 11:58:58 GMT
• Title: OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation
• Authors: Qinglin Zhang, Luyao Cheng, Chong Deng, Qian Chen, Wen Wang, Siqi Zheng, Jiaqing Liu, Hai Yu, Chaohong Tan,
• Abstract summary: Full spoken dialogue systems significantly mirror human-human interactions. achieving low latency and natural interactions is a significant challenge. End-to-end full-to-end spoken dialogue systems are a promising direction for developing efficient and natural end-to-end systems. Audio samples of dialogues generated by OmniFlatten can be found at this web site.
• Score: 24.68804661538364
• License:
• Abstract: Full-duplex spoken dialogue systems significantly advance over traditional turn-based dialogue systems, as they allow simultaneous bidirectional communication, closely mirroring human-human interactions. However, achieving low latency and natural interactions in full-duplex dialogue systems remains a significant challenge, especially considering human conversation dynamics such as interruptions, backchannels, and overlapping speech. In this paper, we introduce a novel End-to-End GPT-based model OmniFlatten for full-duplex conversation, capable of effectively modeling the complex behaviors inherent to natural conversations with low latency. To achieve full-duplex communication capabilities, we propose a multi-stage post-training scheme that progressively adapts a text-based large language model (LLM) backbone into a speech-text dialogue LLM, capable of generating text and speech in real time, without modifying the architecture of the backbone LLM. The training process comprises three stages: modality alignment, half-duplex dialogue learning, and full-duplex dialogue learning. Throughout all training stages, we standardize the data using a flattening operation, which allows us to unify the training methods and the model architecture across different modalities and tasks. Our approach offers a straightforward modeling technique and a promising research direction for developing efficient and natural end-to-end full-duplex spoken dialogue systems. Audio samples of dialogues generated by OmniFlatten can be found at this web site (https://omniflatten.github.io/).

Related papers

• WavChat: A Survey of Spoken Dialogue Models [66.82775211793547]
  Recent advancements in spoken dialogue models, exemplified by systems like GPT-4o, have captured significant attention in the speech domain. These advanced spoken dialogue models not only comprehend audio, music, and other speech-related features, but also capture stylistic and timbral characteristics in speech. Despite the progress in spoken dialogue systems, there is a lack of comprehensive surveys that systematically organize and analyze these systems.
  arXiv  Detail & Related papers  (2024-11-15T04:16:45Z)
• Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents [12.555910887280199]
  We propose Synchronous LLMs for full-sync spoken dialogue modeling. We train a model that generates meaningful and natural spoken dialogue with just 2k hours of real-world spoken dialogue data. We demonstrate the model's ability to participate in full-sync dialogue by simulating interaction between two agents trained on different datasets.
  arXiv  Detail & Related papers  (2024-09-23T23:01:31Z)
• Language Model Can Listen While Speaking [17.584201137311286]
  Listen-while-speaking language model (LSLM) is an end-to-end system equipped with both listening and speaking channels. Our results highlight LSLM's capability to achieve duplex communication with minimal impact on existing systems.
  arXiv  Detail & Related papers  (2024-08-05T16:47:22Z)
• Integrating Paralinguistics in Speech-Empowered Large Language Models for Natural Conversation [46.93969003104427]
  This paper introduces an extensive speech-text LLM framework, the Unified Spoken Dialog Model (USDM) USDM is designed to generate coherent spoken responses with naturally occurring prosodic features relevant to the given input speech. Our approach effectively generates natural-sounding spoken responses, surpassing previous and cascaded baselines.
  arXiv  Detail & Related papers  (2024-02-08T14:35:09Z)
• Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model [8.180382743037082]
  This paper explores the potential of constructing an AI spoken dialogue system that "thinks how to respond" and "thinks how to speak" simultaneously.
  arXiv  Detail & Related papers  (2023-09-20T01:48:27Z)
• ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Human [76.62897301298699]
  ChatPLUG is a Chinese open-domain dialogue system for digital human applications that instruction finetunes on a wide range of dialogue tasks in a unified internet-augmented format. We show that modelname outperforms state-of-the-art Chinese dialogue systems on both automatic and human evaluation. We deploy modelname to real-world applications such as Smart Speaker and Instant Message applications with fast inference.
  arXiv  Detail & Related papers  (2023-04-16T18:16:35Z)
• Channel-aware Decoupling Network for Multi-turn Dialogue Comprehension [81.47133615169203]
  We propose compositional learning for holistic interaction across utterances beyond the sequential contextualization from PrLMs. We employ domain-adaptive training strategies to help the model adapt to the dialogue domains. Experimental results show that our method substantially boosts the strong PrLM baselines in four public benchmark datasets.
  arXiv  Detail & Related papers  (2023-01-10T13:18:25Z)
• Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling [80.51094098799736]
  We propose Bidirectional Information Decoupling Network (BiDeN) as a universal dialogue encoder. BiDeN explicitly incorporates both the past and future contexts and can be generalized to a wide range of dialogue-related tasks. Experimental results on datasets of different downstream tasks demonstrate the universality and effectiveness of our BiDeN.
  arXiv  Detail & Related papers  (2022-04-18T03:51:46Z)
• Dialogue-oriented Pre-training [70.03028879331339]
  We propose three strategies to simulate the conversation features on general plain text. Dialog-PrLM is fine-tuned on three public multi-turn dialogue datasets.
  arXiv  Detail & Related papers  (2021-06-01T12:02:46Z)
• Video-Grounded Dialogues with Pretrained Generation Language Models [88.15419265622748]
  We leverage the power of pre-trained language models for improving video-grounded dialogue. We propose a framework by formulating sequence-to-grounded dialogue tasks as a sequence-to-grounded task. Our framework allows fine-tuning language models to capture dependencies across multiple modalities.
  arXiv  Detail & Related papers  (2020-06-27T08:24:26Z)

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.