BROWSE
Detail
Conference Paper
Efficient and Scalable Neural Residual Waveform Coding with Collaborative Quantization
Cited 18 time in 
Share 
Share
- Authors
- Kai Zhen, Mi Suk Lee, Jongmo Sung, Seungkwon Beack, Minje Kim
- Issue Date
- 2020-05
- Citation
- International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2020, pp.361-365
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- 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.
- KSP Keywords
- AMR-WB, Computational capacity, Digital signal processing methods, Domain-specific, Generative models, Neural network model, Scale-up, model complexity, neural network(NN), speech codec, wide range