ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Efficient and Scalable Neural Residual Waveform Coding with Collaborative Quantization
Cited 18 time in scopus Share share facebook twitter linkedin kakaostory
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
DOI
https://dx.doi.org/10.1109/ICASSP40776.2020.9054347
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