scholarly journals Noise Reduction from Speech Signals using Modified Spectral Subtraction Technique

2018 ◽  
Vol 3 (7) ◽  
pp. 78
Author(s):  
Chowdhury Shahriar Muzammel ◽  
Mahmudul Hasan ◽  
Khalil Ahammad ◽  
Mousumi Hasan Mukti
Keyword(s):  
White Noise ◽  
Noise Reduction ◽  
Speech Signal ◽  
Gaussian White Noise ◽  
Research Work ◽  
Spectral Subtraction ◽  
Experimental Result ◽  
Subtraction Method ◽  
Color Noise ◽  
Spectral Subtraction Method

Varieties of environmental sources of noise and distortion can degrade the quality of the speech signal in a communication system. This research work explores the effects of these interfering sounds on speech applications and introduces a technique for reducing their influence and enhancing the acceptability and intelligibility of the speech signal. In this work, a noise reduction system using single microphone method in time domain to improve SNR of noise contaminated speech is proposed. Traditional Spectral Subtraction method has been reviewed very well and the relationship with wiener filter is also illustrated. The Spectral Subtraction method has been generalized and the focus is put on reducing noise from speech in single channel signals. Voice Activity Detector (VAD) is ignored in this proposed system, because a-priori information about the noise is assumed. The research has been conducted using Gaussian White Noise and Color Noise. The experimental result shows a remarkable improvement in SNR for the generalized version and it is noticed that the result is very much satisfactory when white noises are added but the addition of color noise produces a comparatively poor improvement report. The system has been tested with eight different datasets and on an average, 65.27% improvement in SNR (Signal to Noise Ratio) for White Noise using Generalized Spectral Subtraction Method is achieved comparing with Traditional Spectral Subtraction Method. The average improvement in SNR for Color Noise recorded is 53.31%. The Generalized Spectral Subtraction method is shown to improve the speech quality and to improve SNR as well.

Nonlinear Spectral Subtraction Method for Elimination of Aircraft Engine’s Noise from Degraded Speech Signals

2011 ◽  
Vol 130-134 ◽  
pp. 1327-1330
Author(s):  
Xiu Ying Zhao ◽  
Hong Yu Wang ◽  
Shou Yu Tong ◽  
De You Fu ◽  
Hai Shen Zhou
Keyword(s):  
Frequency Spectrum ◽  
Speech Signal ◽  
The Other ◽  
Spectral Subtraction ◽  
Subtraction Method ◽  
Nonlinear Method ◽  
Input Noise ◽  
Degraded Speech ◽  
Main Input ◽  
Spectral Subtraction Method

The spectral subtraction is one of the best methods for elimination of approximate cyclical engine’s noise from degraded speech signal. Here we turn to research about the nonlinear spectral subtraction method and its improved model. After studying the nonlinear method we turn to this method that whether it can improve the quality of enhanced speech signal, propose the short-time spectral subtraction, which needs two inputs. The main input is containing the voice that is corrupted by noise. The other input (noise reference input) contains noise related in some way to that of the main input (background noise). Then use the main input’s frequency spectrum subtract the other input’s frequency spectrum. The results of experiment have proved it’s effective.

Nonlinear spectral subtraction method for colored noise reduction using multi-band Bark scale

2008 ◽  
Vol 88 (5) ◽  
pp. 1299-1303 ◽  
Author(s):  
Radu Mihnea Udrea ◽  
Nicolae Vizireanu ◽  
Silviu Ciochina ◽  
Simona Halunga
Keyword(s):  
Noise Reduction ◽  
Colored Noise ◽  
Spectral Subtraction ◽  
Subtraction Method ◽  
Spectral Subtraction Method ◽  
Multi Band

Enhancing Speech Quality Using Artificial Bandwidth Expansion with Deep Shallow Convolution Neural Network Framework

2021 ◽  
pp. 2250008
Author(s):  
N. Radha ◽  
R. B. Jananie ◽  
A. Anto Silviya
Keyword(s):  
Neural Network ◽  
Speech Enhancement ◽  
Speech Signal ◽  
Speech Quality ◽  
Convolution Neural Network ◽  
Spectral Subtraction ◽  
Artificial Noise ◽  
Subtraction Method ◽  
Bandwidth Expansion ◽  
Spectral Subtraction Method

Speech processing is an important application area of digital signal processing that helps examine and analyze the speech signal. In this processing, speech enhancement is an essential factor because it improves the quality of the signal that helps resolve the communication challenges. Different speech enhancement algorithms are utilized in the research field, but limited processing capabilities, maximum microphone distance, and voice-first I.O. interfaces create the computation complexity. In this paper, speech enhancement is done in two steps. In an initial step, spectral subtraction method is applied to LJ Speech dataset. In the first stage, noise spectrum is estimated during pauses and it is subtracted from the noisy speech signal to obtain the clean speech signal. However, spectral subtraction method still introduces artificial noise and narrow-band noise in the spectrum. Hence, artificial bandwidth expansion with a deep shallow convolution neural network (ABE-DSCNN) is implemented as a second stage in the paper. Further, developed system is compared with conventional enhancement approaches such as deep learning network (DNN), neural beam forming (NB) and generative adversarial network (GAN). The experimental results show that an ABS-DSCNN provides 4% increase of PSEQ and error rate improved by 40% to 56% with respect to the other existing algorithms for 1000 speech samples. Hence, the paper concludes that ABE-DSCNN approach effectively improves the speech quality.

Sign in / Sign up

Export Citation Format

Share Document