Featherwave: An Efficient High-fidelity Neural Vocoder With Multi-band Linear Prediction

Abstract

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 s

Stats

• citations12
• S2 citations—
• github stars0
• HF likes0
• heat score8.35
• arxiv keytian2020featherwave

Related papers

• Lpcnet: Improving Neural Speech Synthesis Through Linear Prediction (2018)0.00
• High-fidelity And Low-latency Universal Neural Vocoder Based On Multiband Wavernn With Data-driven Linear Prediction For Discrete Waveform Modeling (2021)6.77
• A Real-time Wideband Neural Vocoder At 1.6 Kb/s Using Lpcnet (2019)12.61
• Lp-wavenet: Linear Prediction-based Wavenet Speech Synthesis (2018)0.00
• Fbwave: Efficient And Scalable Neural Vocoders For Streaming Text-to-speech On The Edge (2020)0.00
• End-to-end Lpcnet: A Neural Vocoder With Fully-differentiable LPC Estimation (2022)7.16
• Low-latency Real-time Non-parallel Voice Conversion Based On Cyclic Variational Autoencoder And Multiband Wavernn With Data-driven Linear Prediction (2021)6.77
• Univnet: A Neural Vocoder With Multi-resolution Spectrogram Discriminators For High-fidelity Waveform Generation (2021)14.80