Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder

DOI DOI PDF 被引用文献1件 オープンアクセス

書誌事項

公開日
2023-06-04
権利情報
  • https://doi.org/10.15223/policy-029
  • https://doi.org/10.15223/policy-037
DOI
  • 10.1109/icassp49357.2023.10095298
  • 10.48550/arxiv.2210.15533
公開者
IEEE

説明

Our previous work, the unified source-filter GAN (uSFGAN) vocoder, introduced a novel architecture based on the source-filter theory into the parallel waveform generative adversarial network to achieve high voice quality and pitch controllability. However, the high temporal resolution inputs result in high computation costs. Although the HiFi-GAN vocoder achieves fast high-fidelity voice generation thanks to the efficient upsampling-based generator architecture, the pitch controllability is severely limited. To realize a fast and pitch-controllable high-fidelity neural vocoder, we introduce the source-filter theory into HiFi-GAN by hierarchically conditioning the resonance filtering network on a well-estimated source excitation information. According to the experimental results, our proposed method outperforms HiFi-GAN and uSFGAN on a singing voice generation in voice quality and synthesis speed on a single CPU. Furthermore, unlike the uSFGAN vocoder, the proposed method can be easily adopted/integrated in real-time applications and end-to-end systems.

Accepted to ICASSP 2023

収録刊行物

被引用文献 (1)*注記

もっと見る

キーワード

問題の指摘

ページトップへ