Speech Enhancement with Intelligent Neural Homomorphic Synthesis

10/28/2022
by   Shulin He, et al.
0

Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement. Specifically, we use homomorphic signal processing and cepstral analysis to obtain noisy speech's excitation and vocal tract. Unlike traditional signal processing, we use an attentive recurrent network (ARN) model predicted ratio mask to replace the liftering separation function. Then two convolutional attentive recurrent network (CARN) networks are used to predict the excitation and vocal tract of clean speech, respectively. The system's output is synthesized from the estimated excitation and vocal. Experiments prove that our proposed method performs better, with SI-SNR improving by 1.363dB compared to FullSubNet.

READ FULL TEXT
research
05/11/2020

Online Monaural Speech Enhancement Using Delayed Subband LSTM

This paper proposes a delayed subband LSTM network for online monaural (...
research
06/20/2019

Parameter Enhancement for MELP Speech Codec in Noisy Communication Environment

In this paper, we propose a deep learning (DL)-based parameter enhanceme...
research
10/25/2021

Multichannel Speech Enhancement without Beamforming

Deep neural networks are often coupled with traditional spatial filters,...
research
07/28/2020

Neural Kalman Filtering for Speech Enhancement

Statistical signal processing based speech enhancement methods adopt exp...
research
04/06/2022

FFC-SE: Fast Fourier Convolution for Speech Enhancement

Fast Fourier convolution (FFC) is the recently proposed neural operator ...
research
03/04/2022

Integrating Statistical Uncertainty into Neural Network-Based Speech Enhancement

Speech enhancement in the time-frequency domain is often performed by es...
research
08/18/2019

Efficient Context Aggregation for End-to-End Speech Enhancement Using a Densely Connected Convolutional and Recurrent Network

In speech enhancement, an end-to-end deep neural network converts a nois...

Please sign up or login with your details

Forgot password? Click here to reset