用音频大模型评估语音对话系统的智商情商,准确率提升近40%。
WavReward: Spoken Dialogue Models With Generalist Reward Evaluators
- 基于音频语言模型构建多样本反馈的奖励机制,实现对语音对话的深度评估。
- 在30K条语音对话偏好数据上训练,客观准确率从53.4%提升至91.5%。
- 适合语音对话系统研发者、评估工具开发者使用,尤其关注非文本交互质量。
端到端语音对话模型如GPT-4o-audio近期在语音领域备受关注,但其对话性能的评估长期被忽视。主要原因在于智能聊天机器人传递大量非文本信息,难以用文本模型如ChatGPT衡量。为此,我们提出WavReward,一种基于音频语言模型的通用奖励评估器,可同时评估语音对话系统的智商(IQ)与情商(EQ)。具体而言,1)基于音频语言模型,WavReward引入深度推理过程与非线性奖励机制进行后训练,通过强化学习算法的多样本反馈,构建专用于语音对话模型的评估器;2)我们提出了ChatReward-30K,一个用于训练WavReward的偏好数据集,涵盖理解与生成两个维度,涉及文本聊天、九种声学属性指令聊天及隐含语义聊天等多种任务。WavReward在多个语音对话场景中超越现有最先进评估模型,客观准确率相较Qwen2.5-Omni提升约38.1个百分点(从53.4%增至91.5%),主观A/B测试中领先83%。全面消融实验验证了各组件必要性。所有数据与代码将在论文接受后公开于https://github.com/jishengpeng/WavReward。
原文摘要 · Abstract (English)
End-to-end spoken dialogue models such as GPT-4o-audio have recently garnered significant attention in the speech domain. However, the evaluation of spoken dialogue models' conversational performance has largely been overlooked. This is primarily due to the intelligent chatbots convey a wealth of non-textual information which cannot be easily measured using text-based language models like ChatGPT. To address this gap, we propose WavReward, a reward feedback model based on audio language models that can evaluate both the IQ and EQ of spoken dialogue systems with speech input. Specifically, 1) based on audio language models, WavReward incorporates the deep reasoning process and the nonlinear reward mechanism for post-training. By utilizing multi-sample feedback via the reinforcement learning algorithm, we construct a specialized evaluator tailored to spoken dialogue models. 2) We introduce ChatReward-30K, a preference dataset used to train WavReward. ChatReward-30K includes both comprehension and generation aspects of spoken dialogue models. These scenarios span various tasks, such as text-based chats, nine acoustic attributes of instruction chats, and implicit chats. WavReward outperforms previous state-of-the-art evaluation models across multiple spoken dialogue scenarios, achieving a substantial improvement about Qwen2.5-Omni in objective accuracy from 53.4$\%$ to 91.5$\%$. In subjective A/B testing, WavReward also leads by a margin of 83$\%$. Comprehensive ablation studies confirm the necessity of each component of WavReward. All data and code will be publicly at https://github.com/jishengpeng/WavReward after the paper is accepted.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。