English

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

Audio and Speech Processing 2022-07-08 v1 Machine Learning Sound Signal Processing

Abstract

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.

Keywords

Cite

@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/

R2 v1 2026-06-24T12:17:13.449Z