Efficient And Scalable Neural Residual Waveform Coding With Collaborative Quantization

Abstract

Scalability and efficiency are desired in neural speech codecs, which supports a wide range of bitrates for applications on various devices. We propose a collaborative quantization (CQ) scheme to jointly learn the codebook of LPC coefficients and the corresponding residuals. CQ does not simply shoehorn LPC to a neural network, but bridges the computational capacity of advanced neural network models and traditional, yet efficient and domain-specific digital signal processing methods in an integrated manner. We demonstrate that CQ achieves much higher quality than its predecessor at 9 kbps with even lower model complexity. We also show that CQ can scale up to 24 kbps where it outperforms AMR-WB and Opus. As a neural waveform codec, CQ models are with less than 1 million parameters, significantly less than many other generative models.

Accepted in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) , Barcelona, Spain, May 4-8, 2020

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• WaveNet: A Generative Model for Raw Audio
• Neural Discrete Representation Learning
• Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decoder
• Efficient Neural Audio Synthesis
• Speex: A Free Codec For Free Speech
• High-Quality, Low-Delay Music Coding in the Opus Codec
• Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding