Raw Waveform-based Speech Enhancement By Fully Convolutional Networks

Abstract

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 in

Stats

• citations164
• S2 citations—
• github stars0
• HF likes0
• heat score16.63
• arxiv keyfu2017raw

Related papers

• Multichannel Speech Enhancement By Raw Waveform-mapping Using Fully Convolutional Networks (2019)12.25
• End-to-end Waveform Utterance Enhancement For Direct Evaluation Metrics Optimization By Fully Convolutional Neural Networks (2017)18.00
• TFCN: Temporal-frequential Convolutional Network For Single-channel Speech Enhancement (2022)0.00
• Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks (2020)5.84
• Rawnet: Advanced End-to-end Deep Neural Network Using Raw Waveforms For Text-independent Speaker Verification (2019)15.34
• Speech Denoising With Deep Feature Losses (2018)14.23
• Dmf-net: A Decoupling-style Multi-band Fusion Model For Full-band Speech Enhancement (2022)7.16
• Wavecrn: An Efficient Convolutional Recurrent Neural Network For End-to-end Speech Enhancement (2020)14.02