Raw Waveform-based Speech Enhancement by Fully Convolutional Networks

by   Szu-Wei Fu, et al.

This study proposes a fully convolutional network (FCN) model for raw waveform-based speech enhancement. The proposed system performs speech enhancement in an end-to-end (i.e., waveform-in and waveform-out) manner, which dif-fers from most existing denoising methods that process the magnitude spectrum (e.g., log power spectrum (LPS)) only. Because the fully connected layers, which are involved in deep neural networks (DNN) and convolutional neural networks (CNN), may not accurately characterize the local information of speech signals, particularly with high frequency components, we employed fully convolutional layers to model the waveform. More specifically, FCN consists of only convolutional layers and thus the local temporal structures of speech signals can be efficiently and effectively preserved with relatively few weights. Experimental results show that DNN- and CNN-based models have limited capability to restore high frequency components of waveforms, thus leading to decreased intelligibility of enhanced speech. By contrast, the proposed FCN model can not only effectively recover the waveforms but also outperform the LPS-based DNN baseline in terms of short-time objective intelligibility (STOI) and perceptual evaluation of speech quality (PESQ). In addition, the number of model parameters in FCN is approximately only 0.2 DNN and CNN.


page 3

page 4


Multichannel Speech Enhancement by Raw Waveform-mapping using Fully Convolutional Networks

In recent years, waveform-mapping-based speech enhancement (SE) methods ...

DDKtor: Automatic Diadochokinetic Speech Analysis

Diadochokinetic speech tasks (DDK), in which participants repeatedly pro...

End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks

Speech enhancement model is used to map a noisy speech to a clean speech...

Exploiting Hybrid Models of Tensor-Train Networks for Spoken Command Recognition

This work aims to design a low complexity spoken command recognition (SC...

A study on speech enhancement using exponent-only floating point quantized neural network (EOFP-QNN)

Numerous studies have investigated the effectiveness of neural network q...

Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processing

This work focuses on designing low complexity hybrid tensor networks by ...

Learning Spatiotemporal Features of Ride-sourcing Services with Fusion Convolutional Network

In order to collectively forecast the demand of ride-sourcing services i...

Please sign up or login with your details

Forgot password? Click here to reset