Efficient And Scalable Neural Residual Waveform Coding With Collaborative Quantization

02/13/2020
by   Kai Zhen, et al.
1

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/27/2021

Scalable and Efficient Neural Speech Coding

This work presents a scalable and efficient neural waveform codec (NWC) ...
research
11/25/2019

Neural Percussive Synthesis Parameterised by High-Level Timbral Features

We present a deep neural network-based methodology for synthesising perc...
research
05/12/2019

Improving Opus Low Bit Rate Quality with Neural Speech Synthesis

The voice mode of the Opus audio coder can compress wideband speech at b...
research
06/24/2022

Computational Complexity Evaluation of Neural Network Applications in Signal Processing

In this paper, we provide a systematic approach for assessing and compar...
research
03/16/2022

Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling

Deep learning methods have been employed in gravitational-wave astronomy...
research
01/08/2019

Learning with Collaborative Neural Network Group by Reflection

For the present engineering of neural systems, the preparing of extensiv...
research
12/07/2022

COMPAQT: Compressed Waveform Memory Architecture for Scalable Qubit Control

On superconducting architectures, the state of a qubit is manipulated by...

Please sign up or login with your details

Forgot password? Click here to reset