Enhancing into the Codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders
Authors:
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 711-715
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.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- A Real-Time Wideband Neural Vocoder at 1.6kb/s Using LPCNet2019
- Unsupervised Speech Representation Learning Using WaveNet AutoencodersIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
- LPCNET: Improving Neural Speech Synthesis through Linear Prediction2019
- Low Bit-rate Speech Coding with VQ-VAE and a WaveNet Decoder2019
- A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancement2018
- Wavenet Based Low Rate Speech Coding2018
- Audio Set: An ontology and human-labeled dataset for audio events2017
- Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR2015
- Librispeech: An ASR corpus based on public domain audio books2015
- A Regression Approach to Speech Enhancement Based on Deep Neural NetworksIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014