Seminar Topics & Project Ideas On Computer Science Electronics Electrical Mechanical Engineering Civil MBA Medicine Nursing Science Physics Mathematics Chemistry ppt pdf doc presentation downloads and Abstract

PRESENTED BY:
K.AKILA
N.DEEPTHA
D.NARMADA

---

[attachment=9405]
 NOISE REDUCTION IN SPEECH
• Noise is an unwanted disturbance superimposed on a
useful signal, which tends to obscure its information
content.
• The background noise is the most common factor
degrading the quality and intelligibility of speech .
• The noise reduction technique intends to lower the
noise level without affecting the quality of speech signal.
OBJECTIVE
• To achieve intelligibility, naturalness and overall
perceptual quality of the speech signal.
• To improve the signal strength.
 NOISE DATA
 Factory Noise
 HF Channel Noise
 Babble Noise
 White Noise
 Pink Noise
 Car Interior Noise
 Cockpit Noise
 N.S - Noisy Speech
A.C - Approximation Coefficients
D.C - Detail Coefficients
ICA - Independent Component Analysis
ZCR - Zero Crossing Rate
N.R.S - Noise Reduced Speech
 STANDARD DATABASE
SPEECH SIGNAL :
TEXT : SHE HAD YOUR DARK SUIT IN GREASY WASH
WATER ALL YEAR
SAMPLE LENGTH : 63488 samples
SAMPLING FREQUENCY :16000Hz
VARIANCE :E(X2)-(E(X))2
Variance of the SPEECH SIGNAL(in dB) : -74.5232
 ORIGINAL SPEECH SIGNAL
 FREQUENCIES IN THE SPEECH SIGNAL
 FREQUENCIES IN THE NOISE
 NOISY SPEECH SIGNAL
 FREQUENCIES IN THE NOISY SPEECH
 VARIANCE :E(X2)-(E(X))2
Variance of the SPEECH SIGNAL(in dB) : -74.5232
Variance of the NOISE(in dB) : -106.1482
Variance of the NOISY SPEECH(in dB) : -74.1012
FRAMING
NON-OVERLAPPING FRAMES OF 16msec DURATION.
NUMBER OF FRAMES :248
 WAVELET DECOMPOSITION
 WAVELET USED - DAUBECHIES WAVELET db1
DECOMPOSITION LEVEL - LEVEL 2
 APPROXIMATION COEFFICIENTS :
Correspond to speech combined with low frequency noise in the frequency band (0-2000Hz).
DETAIL COEFFICIENTS :
Correspond to the contribution due to speech in the frequency band (2000-4000Hz).
 WAVELET RECONSTRUCTION
APPROXIMATION COEFFICIENTS AND DETAIL
COEFFICIENTS are UPSAMPLED.
 RECONSTRUCTED SIGNAL
Variance of the RECONSTRUCTED
SIGNAL in(0-2000 Hz) (in dB) : -76.4146
 EXTRACTION OF NOISE FROM NOISY SPEECH
 To analyze the noise frequencies, we need to extract the noise from noisy speech.
 Wavelet transform of LEVEL 2 is used to extract the speech in low frequency band (0-2000 Hz) and to find the starting frame.
 A Modified probability density function is calculated.
 A negative wavelet entropy computed using modified probability density function is used for determining the starting frame.
 MODIFIED PROBABILITY DENSITY FUNCTION
i-frame number
j-sample in a frame
Wi(j) –wavelet energy of the jth sample in ith frame
K-positive constant=1.8
 NEGATIVE ENTROPY CALCULATION
The negative wavelet entropy is given as

E(i) = Pi(j)*log(Pi(j))

Pi(j) -Modified probability function
 The negative wavelet entropy is more negative for noise and silence frames and less negative for speech frames.
 Starting frame is determined from the entropy comparison
ENTROPY PLOT
DETERMINING THE STARTING FRAME
A THRESHOLD is set
THRESHOLD=(MEAN(entropy)+MEDIAN(entropy))/2
THRESHOLD= -74.32
STARTING FRAME :46
The ending frame is also determined.
END FRAME : 234
BOUNDARY PLOT
CONCLUSION
Variance of the NOISY SPEECH(in dB)= -74.1012
Variance of the RECONSTRUCTED = -76.4146
SIGNAL from wavelet decomposition (in dB)
There is an improvement in the intelligibility of the noisy speech which is proved by hearing the speech at each stage.