Summer Research Project. Final Presentation 2013

Detection of Alertness Based on Analysis of Speech Signal

Pulak Sarangi

Ojaswa Anand

Induja Sreekant

Bibek Kabi

Under the Guidance ofProf. Aurobinda RoutrayDepartment of Electrical EngineeringIndian Institute of Technology Kharagpur

Objectives

• Design and Develop System Capable ofdetecting alertness of a person by analyzingthe speech signal

• Implementation on GPU

• Implement the system on STM32Edevelopment board

• Implementation as app on Android 4.2(Jelly Bean, target API 17)

Work PlanWeek 1 • Literature Survey

Week 2 • Formulation of Algorithm

Week 3 • Algorithm testing on MATLAB

Week 4 • Conversion of MATLAB code to C code• Conversion of MATLAB code to JAVA code

Week 5 • Implementation on GPU• Implementation on STM32E• Implementation on Android platform

1. Model As Implemented in MATLAB and C/C++

RecordingFormation of

Henkel Matrix

Noise Removal

using SVD

De-framing for Enhanced

Signal

Framing & Windowing

Extraction of Wavelet Features

Classificationof voiced/ silence

parts based on energy

S(n)

Selection of Wavelet Features

Enhanced Speech

Segmentation of speech signal

into overlapping

samples

6 level Decomposition of signal using

Daubechies wavelet

Computation of ratio of 62.5-

1000Hz energy to the total energy

E(i)

Comparison with

threshold

VoicedSilence

E(i) input

>0.8<0.3

Single Segment with same pre

& post segment

Series Segment with same pre

& post segment

Single or Series with different

pre & post segment

Classification

PROGRESS• Fully Functional MATLAB & C/C++ code

• Fully Functional Java Code

• Literature survey for implementation of C/JAVA code onto

Embedded/ANDROID platform and GPU respectively.

ResultsVoiced Silence

288 311

186 413

151 448

54 545

Speech Signal

2. Model As Implemented in MATLAB and C/C++

RecordingFormation of

Henkel Matrix

Noise Removal

using SVD

De-framing for Enhanced

Signal

Framing & Windowing

Feature Extraction (MFCCs, LPCCs)

Classificationof voiced/ silence

parts based on Generalized Eigenvalue

S(n)

Observation• After feature extraction instead of independent statistical properties

like mean, standard deviation, kurtosis, etc. covariance property was

taken into consideration, making processing much faster.

ResultsDistance between covariance matrices

4.013

6.831

Speech Signal

PROGRESS• Fully Functional MATLAB

• Literature survey for implementation of C/C++ code in GPU

3. Model As Implemented in MATLAB and C/C++

RecordingFormation of

Henkel Matrix

Noise Removal

using SVD

De-framing for Enhanced

Signal

Framing & Windowing

Feature extraction (MFCCs, LPCCs)

Classificationof voiced/ silence parts by GMM, SVM classifier

S(n)

PROGRESS• Fully Functional MATLAB code

• Literature survey for implementation of C/C++ code in GPU

PLAN FOR FURTHER WORK• Implementation on GPU

• Implementation on STM32E development board

• Implementation as Android App for Android 4.2(API 17, Jelly Bean)

• Comparison of Results with other algorithms

Thank You

Voiced and Unvoiced Sounds• Fundamental difference :

o Vibrations of the vocal cords produce voiced sounds. o Rate at which the vocal cords vibrate dictates the pitch of the sound.o Unvoiced sounds do not rely on the vibration of the vocal cords. o Unvoiced sounds are created by the constriction of the vocal tract. o Vocal cords remain open and the constrictions of the vocal tract force air out to produce

the unvoiced sounds

• The fundamental frequency of voiced segments is ranged from 60-500Hz• The ratio between the energy of the bands between 62.5 Hz and 1000Hz to that of all bands

is computed and used in our algorithm as the fundamental parameter in formulating the V/UV decision.

Literature Review

• Speech Enhancement using Singular ValueDecomposition(SVD)

• Wavelet based Voiced/Unvoiced ClassificationAlgorithm