Neural Homomorphic Vocoder

By Zhijun Liu, Kuan-Ting Chen, Kai Yu. 2020

26 citations recorded by the source corpus.

In this paper, we propose the neural homomorphic vocoder (NHV), a source-filter model based neural vocoder framework. NHV synthesizes speech by filtering impulse trains and noise with linear time-varying (LTV) filters. A neural network controls the LTV filters by estimating complex cepstrums of time-varying impulse responses given acoustic features. The proposed framework can be trained with a combination of multi-resolution STFT loss and adversarial loss functions. Due to the use of DSP-based synthesis methods, NHV is highly efficient, fully controllable and interpretable. A vocoder was built under the framework to synthesize speech given log-Mel spectrograms and fundamental frequencies. While the model cost only 15 kFLOPs per sample, the synthesis quality remained comparable to baseline neural vocoders in both copy-synthesis and text-to-speech.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Chenpeng Du
6. K. Yu
7. Yiwei Guo
8. Sheng Zhao

In Signal Processing

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Yiwei Guo
6. Chenpeng Du
7. K. Yu
8. Xie Chen

Citations in the corpus

• VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature (2022, background): “Another important type of vocoders is neural source-filter model [9, 10] based on the mechanism of human voice production.”
• A Survey on Neural Speech Synthesis (2021, background): “Other Vocoders Some works leverage neural-based source-filter model for waveform generation [375, 374, 371, 207, 146, 145, 75, 305, 407], aiming to achieve high voice quality while maintaining controllable speech generation.”
• Unified Source-Filter GAN: Unified Source-filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN (2021, background): “Generative adversarial network (GAN) based neural homomorphic vocoder (NHV) [24] first develops neural-based linear-time-variant (LTV) filters with the input pulse trains and white noise to generate mixed source excitations, and then a trainable causal finite impulse response (FIR) filter is applied”