Efficient and Scalable Neural Residual Waveform Coding with Collaborative Quantization
Kai Zhen, Mi Suk Lee, Jongmo Sung, Seungkwon Beack, Minje Kim
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.
BibTeX
@inproceedings{icassp2020_efficientandscal,
title = {Efficient and Scalable Neural Residual Waveform Coding with Collaborative Quantization},
author = {Kai Zhen and Mi Suk Lee and Jongmo Sung and Seungkwon Beack and Minje Kim},
booktitle = {ICASSP 2020},
year = {2020}
}