用可微共振滤波器实现高保真语音合成，精确控制音色特征。
HiFi-Glot: High-Fidelity Neural Formant Synthesis with Differentiable Resonant Filters
- 基于神经声门激励与可微共振滤波器的端到端架构
- 在音质自然度和共振峰控制精度上优于Praat等工具
- 适合需要精细语音调控的研究与工业应用
共振峰合成旨在生成具有可控共振峰结构的语音，从而实现对声道共振和语音特征的精准控制。然而，现有方法虽能精确调节共振峰，却常因未能捕捉复杂的共现声学线索而导致语音质量下降。为此，本文提出HiFi-Glot，一种端到端的神经共振峰合成系统，在保持精确共振峰控制的同时实现高保真语音合成。该模型采用受经典共振峰合成启发的源-滤波器架构：神经声码器生成声门激励信号，可微共振滤波器建模共振峰以输出语音波形。实验表明，所提模型在感知质量和自然度方面优于行业标准工具Praat，同时在共振峰频率控制上更具精度。代码、模型检查点及代表性音频样本已公开于 https://www.yichenggu.com/HiFi-Glot/。
原文摘要 · Abstract (English)
Formant synthesis aims to generate speech with controllable formant structures, enabling precise control of vocal resonance and phonetic features. However, while existing formant synthesis approaches enable precise formant manipulation, they often yield an impoverished speech signal by failing to capture the complex co-occurring acoustic cues essential for naturalness. To address this issue, this letter presents HiFi-Glot, an end-to-end neural formant synthesis system that achieves both precise formant control and high-fidelity speech synthesis. Specifically, the proposed model adopts a source--filter architecture inspired by classical formant synthesis, where a neural vocoder generates the glottal excitation signal, and differentiable resonant filters model the formants to produce the speech waveform. Experiment results demonstrate that our proposed HiFi-Glot model can generate speech with higher perceptual quality and naturalness while exhibiting a more precise control over formant frequencies, outperforming industry-standard formant manipulation tools such as Praat. Code, checkpoints, and representative audio samples are available at https://www.yichenggu.com/HiFi-Glot/.
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。