FeatherWave: An efficient high-fidelity neural vocoder with multi-band linear prediction

By Qiao Tian, Zewang Zhang, Heng Lu, Linghui Chen, Shan Liu. 2020

22 citations recorded by the source corpus.

In this paper, we propose the FeatherWave, yet another variant of WaveRNN vocoder combining the multi-band signal processing and the linear predictive coding. The LPCNet, a recently proposed neural vocoder which utilized the linear predictive characteristic of speech signal in the WaveRNN architecture, can generate high quality speech with a speed faster than real-time on a single CPU core. However, LPCNet is still not efficient enough for online speech generation tasks. To address this issue, we adopt the multi-band linear predictive coding for WaveRNN vocoder. The multi-band method enables the model to generate several speech samples in parallel at one step. Therefore, it can significantly improve the efficiency of speech synthesis. The proposed model with 4 sub-bands needs less than 1.6 GFLOPS for speech generation. In our experiments, it can generate 24 kHz high-fidelity audio 9x faster than real-time on a single CPU, which is much faster than the LPCNet vocoder. Furthermore, our subjective listening test shows that the FeatherWave can generate speech with better quality than LPCNet.

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. Sheng Zhao
6. Hisashi Kawai
7. Takuma Okamoto
8. Yoshinori Shiga

In Signal Processing

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Hisashi Kawai
6. Takuma Okamoto
7. Yoshinori Shiga
8. Tomoki Toda

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “Some following works further improve LPCNet from different perspectives, such as reducing complexity for speedup [364, 269, 148], and improving stability for better quality [126].”
• Noise Level Limited Sub-Modeling for Diffusion Probabilistic Vocoders (2021, background): “In contrast to real-time autoregressive neural vocoders such as WaveRNN [4], LPCNet [5], and FeatherWave [6], non-autoregressive models, which simultaneously synthesize all speech waveform samples, can be easily implemented as real-time neural vocoders, and many models have been investigated.”
• Investigation of Fast and Efficient Methods for Multi-Speaker Modeling and Speaker Adaptation (2021, methodology): “As for the training strategies, previous works either simply update the parameters of the entire models [13] or fix the text encoder during speaker adaptation [17] without investigating any other strategies.”
• Improve GAN-based Neural Vocoder using Pointwise Relativistic LeastSquare GAN (2021, methodology): “Most early studies of neural vocoders are based on autoregressive(AR) models, such as Wavenet[4], WaveRNN[5], SampleRNN[6], FeatherWave[7] etc.”