Recent advancements in zero-shot text-to-speech (TTS) modeling have led to
significant strides in generating high-fidelity and diverse speech. However,
dialogue generation, along with achieving human-like naturalness in speech,
continues to be a challenge in the field. In this paper, we introduce CoVoMix:
Conversational Voice Mixture Generation, a novel model for zero-shot,
human-like, multi-speaker, multi-round dialogue speech generation. CoVoMix is
capable of first converting dialogue text into multiple streams of discrete
tokens, with each token stream representing semantic information for individual
talkers. These token streams are then fed into a flow-matching based acoustic
model to generate mixed mel-spectrograms. Finally, the speech waveforms are
produced using a HiFi-GAN model. Furthermore, we devise a comprehensive set of
metrics for measuring the effectiveness of dialogue modeling and generation.
Our experimental results show that CoVoMix can generate dialogues that are not
only human-like in their naturalness and coherence but also involve multiple
talkers engaging in multiple rounds of conversation. These dialogues, generated
within a single channel, are characterized by seamless speech transitions,
including overlapping speech, and appropriate paralinguistic behaviors such as
laughter. Audio samples are available at this https URL

零样本文本朗读 (TTS) 建模的最新进展在生成高保真和多样化的语音方面取得了重大进展。然而，在实现人类自然性的语音中实现对话生成仍然是该领域的一个挑战。在这篇论文中，我们介绍了一种名为 CoVoMix 的新型模型，用于零样本、人类化、多发言人、多轮对话语音生成。CoVoMix 首先将对话文本转换为多个离散令牌流，每个令牌流代表单个发言人的语义信息。然后，将这些令牌流输入基于流匹配的声学模型，以生成混合的 mel 频谱图。最后，使用 HiFi-GAN 模型生成语音波形。此外，我们设计了一套全面的度量标准来衡量对话建模和生成的效果。我们的实验结果表明，CoVoMix 能够生成自然性和连贯性非常类似于人类的对话，还包括多个发言人参与多轮对话。这些在单个通道内生成的对话以流畅的语音过渡为特点，包括重叠的语音和适当的语言行为，如笑声。音频样本可在此 https URL 查看。