Modular dynamic deep denoising autoencoder for speech enhancement

Deep Denoising Autoencoder (DDAE) is an effective method for noise reduction and speech enhancement. However, a single DDAE with a fixed number of frames for neural network input cannot extract contextual information sufficiently. It has also less generalization in unknown SNRs (signal-to-noise-rati...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2017 7th International Conference on Computer and Knowledge Engineering (ICCKE) S. 254 - 259
Hauptverfasser: Safari, Razieh, Ahadi, Seyed Mohammad, Seyedin, Sanaz
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.10.2017
Schlagworte:
Deep Denoising Autoencoder (DDAE)
Improved Context Pattern
Modular Dynamic Deep Denoising Autoencoder (MD-DDAE)
Neural networks
Noise measurement
Noise reduction
Signal to noise ratio
Speech
Speech enhancement
Training
Unseen Signal to Noise Ratio
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Deep Denoising Autoencoder (DDAE) is an effective method for noise reduction and speech enhancement. However, a single DDAE with a fixed number of frames for neural network input cannot extract contextual information sufficiently. It has also less generalization in unknown SNRs (signal-to-noise-ratio) and the enhanced output has some residual noise. In this paper, we use a modular model in which three DDAEs with different window lengths are stacked. Experimental results showes that our proposed architecture, namely modular dynamic deep denoising autoencoder (MD-DDAE) provides superior performance in comparison with the traditional DDAE models in different noisy conditions.
DOI:10.1109/ICCKE.2017.8167886