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.
@article{arxiv.2207.03282,
title = {NESC: Robust Neural End-2-End Speech Coding with GANs},
author = {Nicola Pia and Kishan Gupta and Srikanth Korse and Markus Multrus and Guillaume Fuchs},
journal= {arXiv preprint arXiv:2207.03282},
year = {2022}
}
Comments
Paper accepted to Interspeech 2022 Please check our demo at: https://fhgspco.github.io/nesc/