· 2013
Speech enhancement based on deep denoising autoencoder
- 870citations
- 2013year
Short summary
A deep denoising autoencoder (DAE) trained with noisy-clean speech pairs significantly outperforms traditional MMSE algorithms in speech enhancement, showing consistent performance gains with increased DAE depth.
AI-generated from the title and abstract; the full text is not read.
Key points
- A denoising deep autoencoder (DAE) was trained using noisy-clean speech pairs, unlike previous methods trained only on clean speech.
- The DAE employs a greedy layer-wise pretraining followed by fine-tuning strategy.
- Deeper DAEs consistently increase performance when a large training dataset is provided.
- The proposed denoising DAE achieved superior performance compared to a minimum mean square error (MMSE) based algorithm on objective evaluations.
AI-generated from the title and abstract; the full text is not read.
Abstract
We previously have applied deep autoencoder (DAE) for noise reduction and speech enhancement. However, the DAE was trained using only clean speech. In this study, we further introduce an explicit denoising process in learning the DAE. In training the DAE, we still adopt greedy layer-wised pretraining plus fine tuning strategy. In pretraining, each layer is trained as a one hidden layer neural autoencoder (AE) using noisy-clean speech pairs as input and output (or transformed noisy-clean speech pairs by preceding AEs). Fine tuning was done by stacking all AEs with pretrained parameters for initialization. The trained DAE is used as a filter for speech estimation when noisy speech is given. Speech enhancement experiments were done to examine the performance of the trained denoising DAE. Noise reduction, speech distortion, and perceptual evaluation of speech quality (PESQ) criteria are used in the performance evaluations. Experimental results show that adding depth of the DAE consistently increase the performance when a large training data set is given. In addition, compared with a minimum mean square error based speech enhancement algorithm, our proposed denoising DAE provided superior performance on the three objective evaluations.
The authors' abstract, as published at the source., 2013 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Signal Processing
Signal ProcessingComputer Science