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

Jonah Casebeer; Vinjai Vale; Umut Isik; Jean-Marc Valin; Ritwik Giri; Arvindh Krishnaswamy

ICASSP 2021accepted0 citations

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

Jonah Casebeer, Vinjai Vale, Umut Isik, Jean-Marc Valin, Ritwik Giri, Arvindh Krishnaswamy

Abstract

Audio codecs based on discretized neural autoencoders have recently been developed and shown to provide significantly higher compression levels for comparable quality speech out-put. 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.

BibTeX

@inproceedings{icassp2021_enhancingintothe,
  title = {Enhancing into the Codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders},
  author = {Jonah Casebeer and Vinjai Vale and Umut Isik and Jean-Marc Valin and Ritwik Giri and Arvindh Krishnaswamy},
  booktitle = {ICASSP 2021},
  year = {2021}
}