Efficient Context Aggregation for End-to-End Speech Enhancement Using a Densely Connected Convolutional and Recurrent Network
Preprint
Abstract
In speech enhancement, an end-to-end deep neural network converts a noisy speech signal to a clean speech directly in time domain without time-frequency transformation or mask estimation. However, aggregating contextual information from a high-resolution time domain signal with an affordable model complexity still remains challenging. In this paper, we propose a hybrid architecture, incorporating densely connected convolutional networks (DenseNet) and gated recurrent units (GRU), to enable dual-level temporal context aggregation. Due to the dense connectivity pattern and a cross-component identical shortcut, the proposed model consistently outperforms competing convolutional baselines with an average STOI improvement of 0.23 and PESQ of 1.38 at three SNR levels. In addition, the proposed hybrid architecture is computationally efficient with 1.38 million parameters.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Gated Residual Networks With Dilated Convolutions for Monaural Speech EnhancementIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2018
- End-To-End Optimized Speech Coding with Deep Neural Networks2018
- SEGAN: Speech Enhancement Generative Adversarial Network2017
- LSTM, GRU, Highway and a Bit of Attention: An Empirical Overview for Language Modeling in Speech Recognition2016
- Complex Ratio Masking for Monaural Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015
- An Algorithm for Intelligibility Prediction of Time–Frequency Weighted Noisy SpeechIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Performance measurement in blind audio source separationIEEE Transactions on Audio, Speech, and Language Processing, 2006
- Suppression of acoustic noise in speech using spectral subtractionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979