HiFi-Glot: 基于可微共振滤波器的高保真神经元元音合成
HiFi-Glot: High-Fidelity Neural Formant Synthesis with Differentiable Resonant Filters
AI总结：
HiFi-Glot通过可微共振滤波器实现高保真神经元音合成，提供精确的元音控制和自然语音生成。
摘要：
元音合成旨在生成具有可控元音结构的语音，从而实现对语音共振和语音特征的精确控制。然而，尽管现有的元音合成方法能够实现精确的元音操控，但往往由于未能捕捉到复杂的同时出现的听觉线索，导致生成的语音信号贫乏，缺乏自然性。为了解决这个问题，本文提出HiFi-Glot，一种端到端的神经元音合成系统，能够实现精确的元音控制和高保真的语音合成。具体而言，所提出的模型采用受经典元音合成启发的源-滤波架构，其中神经语音编码器生成声带激励信号，而可微共振滤波器建模元音以生成语音波形。实验结果表明，所提出的HiFi-Glot模型能够生成具有更高感知质量和自然度的语音，同时在元音频率控制方面更加精确，优于行业标准的元音操控工具，如Praat。代码、检查点和代表性音频样本可在https://www.yichenggu.com/HiFi-Glot/上获取。
英文摘要：
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/.
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。
