A Speech Enhancement System Using Binary Mask Approach and Spectral Subtraction Method

Author

Tsai-Tsung Han ; Pei-Yun Liu

Author_Institution

Electr. Eng., Nat. Central Univ., Chungli, Taiwan

fYear

2014

fDate

10-12 June 2014

Firstpage

1065

Lastpage

1068

Abstract

In this paper, we proposed a speech enhancement system by combining the binary time-frequency mask and spectral subtraction method. It is constructed in Short Time Fourier Transform (STFT) domain with feature extraction assistance. The binary mask approach and spectral subtraction techniques are also applied. Analysis is done on noisy speech signal corrupted by factory noise at -3dB, 0dB and 3dB SNR levels. Simulation and results are performed in MATLAB 7.14 (R2012a). With the output SNR (Signal to Noise Ratio) analysis, we have obtained promising results in real experimental environment.

Keywords

Fourier transforms; feature extraction; speech enhancement; SNR; STFT; Short Time Fourier Transform; binary mask approach; binary time-frequency mask; feature extraction assistance; noisy speech signal; signal to noise ratio analysis; spectral subtraction method; spectral subtraction techniques; speech enhancement system; Noise measurement; Signal to noise ratio; Source separation; Speech; Speech enhancement; Time-frequency analysis; STFT; binary mask approach; blind source separation; spectral subtraction; speech enhancement;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer, Consumer and Control (IS3C), 2014 International Symposium on

Conference_Location

Taichung

Type

conf

DOI

10.1109/IS3C.2014.278

Filename

6846070