Listening to Sounds of Silence for Speech Denoising
arXiv:2010.12013
Abstract
We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications. Our approach is based on a key observation about human speech: there is often a short pause between each sentence or word. In a recorded speech signal, those pauses introduce a series of time periods during which only noise is present. We leverage these incidental silent intervals to learn a model for automatic speech denoising given only mono-channel audio. Detected silent intervals over time expose not just pure noise but its time-varying features, allowing the model to learn noise dynamics and suppress it from the speech signal. Experiments on multiple datasets confirm the pivotal role of silent interval detection for speech denoising, and our method outperforms several state-of-the-art denoising methods, including those that accept only audio input (like ours) and those that denoise based on audiovisual input (and hence require more information). We also show that our method enjoys excellent generalization properties, such as denoising spoken languages not seen during training.
9 pages, 6 figures, accepted in NeurIPS 2020; Sound examples can be found at http://www.cs.columbia.edu/cg/listen_to_the_silence/
References in corpus (7)
- Deep Learning for Audio Signal Processing
- SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
- Audio Spectrogram Representations for Processing with Convolutional Neural Networks
- MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement
- Speech Enhancement using Self-Adaptation and Multi-Head Self-Attention
- AV Speech Enhancement Challenge using a Real Noisy Corpus
- Deep Residual-Dense Lattice Network for Speech Enhancement