用于高保真语音合成的基于声源-滤波器的生成对抗神经声码器
Source-Filter-Based Generative Adversarial Neural Vocoder for High Fidelity Speech Synthesis
AI总结：
本文提出基于声源-滤波器的生成对抗神经声码器SF-GAN，通过引入F0激励信号结合多分辨率卷积滤波器重建波形，在AS和TTS任务中超越HiFi-GAN和Fre-GAN，合成质量媲美真实音频。
摘要：
本文提出了一种基于声源-滤波器的生成对抗神经声码器，名为SF-GAN，它通过将基于F0的声源激励信号引入神经滤波器框架，实现从输入声学特征到高保真波形的生成。SF-GAN声码器由一个声源模块和一个分辨率级条件滤波器模块组成，并基于生成对抗策略进行训练。声源模块根据F0信息产生激励信号，随后分辨率级卷积滤波器模块将激励信号与处理后的声学特征在各种时间分辨率上进行结合，最终重建原始波形。实验结果表明，我们提出的SF-GAN声码器在分析合成（AS）和文本转语音（TTS）任务中均优于最先进的HiFi-GAN和Fre-GAN，且SF-GAN的合成语音质量与真实音频相当。
英文摘要：
This paper proposes a source-filter-based generative adversarial neural vocoder named SF-GAN, which achieves high-fidelity waveform generation from input acoustic features by introducing F0-based source excitation signals to a neural filter framework. The SF-GAN vocoder is composed of a source module and a resolution-wise conditional filter module and is trained based on generative adversarial strategies. The source module produces an excitation signal from the F0 information, then the resolution-wise convolutional filter module combines the excitation signal with processed acoustic features at various temporal resolutions and finally reconstructs the raw waveform. The experimental results show that our proposed SF-GAN vocoder outperforms the state-of-the-art HiFi-GAN and Fre-GAN in both analysis-synthesis (AS) and text-to-speech (TTS) tasks, and the synthesized speech quality of SF-GAN is comparable to the ground-truth audio.
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。
