mlsanityData to 7 Oct 2026

A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate

arXiv 2108.04051 ↗First posted 9 Aug 2021eess.AS cs.LG cs.SDcited by 5

Not on the map. Why?

Abstract (arXiv)

Recently, GAN vocoders have seen rapid progress in speech synthesis, starting to outperform autoregressive models in perceptual quality with much higher generation speed. However, autoregressive vocoders are still the common choice for neural generation of speech signals coded at very low bit rates. In this paper, we present a GAN vocoder which is able to generate wideband speech waveforms from parameters coded at 1.6 kbit/s. The proposed model is a modified version of the StyleMelGAN vocoder that can run in frame-by-frame manner, making it suitable for streaming applications. The experimental results show that the proposed model significantly outperforms prior autoregressive vocoders like LPCNet for very low bit rate speech coding, with computational complexity of about 5 GMACs, providing a new state of the art in this domain. Moreover, this streamwise adversarial vocoder delivers quality competitive to advanced speech codecs such as EVS at 5.9 kbit/s on clean speech, which motivates further usage of feed-forward fully-convolutional models for low bit rate speech coding.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 19 of its 28 references that are in the map. First posted on arXiv 9 Aug 2021.

Builds on

19 of 28 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  3. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  4. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  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. 2020High-Fidelity Generative Image Compressioncited by 331
  8. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  9. 2018Efficient Neural Audio Synthesiscited by 218
  10. 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 109
  11. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 90
  12. 2020Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speechcited by 63
7 more
  1. 2020Streaming keyword spotting on mobile devicescited by 47
  2. 2017Wavenet based low rate speech codingcited by 32
  3. 2020StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalizationcited by 26
  4. 2021Generative Speech Coding with Predictive Variance Regularizationcited by 18
  5. 2019A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNetcited by 16
  6. 2018High-quality speech coding with SampleRNNcited by 14
  7. 2021WARP-Q: Quality Prediction For Generative Neural Speech Codecscited by 12

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 0; 2024: 1; 2025: 2.

5 papers.

  1. 2025FlowDec: A flow-based full-band general audio codec with high perceptual qualitycited by 15
  2. 2022NESC: Robust Neural End-2-End Speech Coding with GANscited by 3
  3. 2024FlowMAC: Conditional Flow Matching for Audio Coding at Low Bit Ratescited by 3
  4. 2022Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexitycited by 1
  5. 2025Real-Time Streaming Mel Vocoding with Generative Flow Matchingcited by 1