mlsanityData to 7 Oct 2026

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

arXiv 2207.03282 ↗First posted 7 Jul 2022eess.AS cs.LG cs.SDcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 22 of its 35 references that are in the map. First posted on arXiv 7 Jul 2022.

Builds on

22 of 35 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Neural Discrete Representation Learningcited by 4,650
  3. 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
  4. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 639
  5. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  6. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  7. 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 182
  8. 2020ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metriccited by 76
  9. 2022ICASSP 2022 Deep Noise Suppression Challengecited by 57
  10. 2019Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decodercited by 47
  11. 2017Wavenet based low rate speech codingcited by 32
  12. 2017End-to-End Optimized Speech Coding with Deep Neural Networkscited by 21
10 more
  1. 2021Generative Speech Coding with Predictive Variance Regularizationcited by 18
  2. 2019A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNetcited by 16
  3. 2019Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Codingcited by 15
  4. 2020Audio Codec Enhancement with Generative Adversarial Networkscited by 11
  5. 2019Improving Opus Low Bit Rate Quality with Neural Speech Synthesiscited by 9
  6. 2020Efficient And Scalable Neural Residual Waveform Coding With Collaborative Quantizationcited by 7
  7. 2021A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Ratecited by 5
  8. 2018Convolutional Neural Networks to Enhance Coded Speechcited by 4
  9. 2022PostGAN: A GAN-Based Post-Processor to Enhance the Quality of Coded Speechcited by 4
  10. 2020Enhancement Of Coded Speech Using a Mask-Based Post-Filtercited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 1.

3 papers.

  1. 2024FlowMAC: Conditional Flow Matching for Audio Coding at Low Bit Ratescited by 3
  2. 2022Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexitycited by 1
  3. 2025On the Design of Diffusion-based Neural Speech Codecscited by 1