DeepAI AI Chat
Log In Sign Up

NESC: Robust Neural End-2-End Speech Coding with GANs

07/07/2022
by   Nicola Pia, et al.
Fraunhofer
0

Neural networks have proven to be a formidable tool to tackle the problem of speech coding at very low bit rates. However, the design of a neural coder that can be operated robustly under real-world conditions remains a major challenge. Therefore, we present Neural End-2-End Speech Codec (NESC) a robust, scalable end-to-end neural speech codec for high-quality wideband speech coding at 3 kbps. The encoder uses a new architecture configuration, which relies on our proposed Dual-PathConvRNN (DPCRNN) layer, while the decoder architecture is based on our previous work Streamwise-StyleMelGAN. Our subjective listening tests on clean and noisy speech show that NESC is particularly robust to unseen conditions and signal perturbations.

READ FULL TEXT
04/15/2016

Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding

Most current very low bit rate (VLBR) speech coding systems use hidden M...
07/05/2022

Ultra-Low-Bitrate Speech Coding with Pretrained Transformers

Speech coding facilitates the transmission of speech over low-bandwidth ...
10/14/2019

Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decoder

In order to efficiently transmit and store speech signals, speech codecs...
11/04/2022

Neural Feature Predictor and Discriminative Residual Coding for Low-Bitrate Speech Coding

Low and ultra-low-bitrate neural speech coding achieves unprecedented co...
03/08/2022

Practical cognitive speech compression

This paper presents a new neural speech compression method that is pract...
02/12/2021

Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders

Audio codecs based on discretized neural autoencoders have recently been...
10/25/2017

End-to-End Optimized Speech Coding with Deep Neural Networks

Modern compression algorithms are often the result of laborious domain-s...