DiffAR：用于原始语音波形生成的去噪扩散自回归模型
DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation
AI总结：
本研究提出用于原始语音波形生成的扩散自回归模型DiffAR，可端到端生成任意时长高保真语音，支持无条件与条件生成，效果优于现有前沿系统。
摘要：
扩散模型近期已被证实可用于高质量语音生成。现有研究大多聚焦于生成频谱图，因此还需要额外的后续模型（即声码器）将频谱图转换为波形。本研究提出一种用于生成原始语音波形的扩散概率端到端模型。该模型为自回归模型，会依次生成重叠帧，每一帧都以先前生成帧的一部分为条件。因此，我们的模型能够有效合成任意时长的语音，同时保持高保真合成效果与时间连贯性。我们实现了该模型的无条件与条件语音生成功能，其中条件生成可由输入的音素、振幅和基频值序列驱动。直接在波形上进行处理具备一些实证优势，具体而言，它能够生成诸如 vocal fry（喉音）这类局部声学特征，使整体波形听起来更自然。此外，所提出的扩散模型是随机而非确定性的，因此每次推理都会生成略有差异的波形变体，可产生大量有效实现。实验表明，与其他前沿神经语音生成系统相比，该模型生成的语音质量更优。
英文摘要：
Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a waveform (i.e., a vocoder). This work proposes a diffusion probabilistic end-to-end model for generating a raw speech waveform. The proposed model is autoregressive, generating overlapping frames sequentially, where each frame is conditioned on a portion of the previously generated one. Hence, our model can effectively synthesize an unlimited speech duration while preserving high-fidelity synthesis and temporal coherence. We implemented the proposed model for unconditional and conditional speech generation, where the latter can be driven by an input sequence of phonemes, amplitudes, and pitch values. Working on the waveform directly has some empirical advantages. Specifically, it allows the creation of local acoustic behaviors, like vocal fry, which makes the overall waveform sounds more natural. Furthermore, the proposed diffusion model is stochastic and not deterministic; therefore, each inference generates a slightly different waveform variation, enabling abundance of valid realizations. Experiments show that the proposed model generates speech with superior quality compared with other state-of-the-art neural speech generation systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
