mlsanityData to 7 Oct 2026

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

arXiv 2102.06610 ↗First posted 12 Feb 2021eess.AS cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Audio codecs based on discretized neural autoencoders have recently been developed and shown to provide significantly higher compression levels for comparable quality speech output. However, these models are tightly coupled with speech content, and produce unintended outputs in noisy conditions. Based on VQ-VAE autoencoders with WaveRNN decoders, we develop compressor-enhancer encoders and accompanying decoders, and show that they operate well in noisy conditions. We also observe that a compressor-enhancer model performs better on clean speech inputs than a compressor model trained only on clean speech.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 12 of its 22 references that are in the map. First posted on arXiv 12 Feb 2021.

Builds on

12 of 22 references.

References · 12

  1. 2017Neural Discrete Representation Learningcited by 4,650
  2. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  3. 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 109
  4. 2019Unsupervised speech representation learning using WaveNet autoencoderscited by 90
  5. 2019Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decodercited by 47
  6. 2017A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancementcited by 34
  7. 2017Wavenet based low rate speech codingcited by 32
  8. 2020PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Losscited by 23
  9. 2019A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNetcited by 16
  10. 2020Unsupervised Acoustic Unit Representation Learning for Voice Conversion using WaveNet Auto-encoderscited by 8
  11. 2020Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Codingcited by 7
  12. 2018Towards achieving robust universal neural vocodingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 1; 2023: 0; 2024: 1; 2025: 2; 2026: 1.

7 papers.

  1. 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
  2. 2025Learning to Upsample and Upmix Audio in the Latent Domaincited by 5
  3. 2022Cross-Scale Vector Quantization for Scalable Neural Speech Codingcited by 3
  4. 2021Cognitive Coding of Speechcited by 2
  5. 2024Exploratory Evaluation of Speech Content Maskingcited by 2
  6. 2025Task and Perception-aware Distributed Source Coding for Correlated Speech under Bandwidth-constrained Channelscited by 1
  7. 2026Pseudo-Quantized Actor-Critic Algorithm for Robustness to Noisy Temporal Difference Errorcited by 0