Classification of place of articulation in unvoiced stops with spectro-temporal surface modeling V. Karjigi, P. Rao Dept. of Electrical Engineering, Indian.

Classification of place of articulation

in unvoiced stops with spectro-temporal surface

modeling

V. Karjigi , P. RaoDept. of Electrical Engineering, Indian Institute of Technology

Bombay, Powai, Mumbai 400076, India Received 8 December 2011; received in revised form 12 March 2012;

accepted 23 April 2012 Available online 1 June 2012

Chairman:Hung-Chi YangPresenter: Yue-Fong GuoAdvisor: Dr. Yeou-Jiunn ChenDate: 2013.3.20

Outline

• Introduction

• MFCC

• 2D-DCT

• Polynomial surface

Outline

• GMM

• Results

• Conclusion

Introduction

• Automatic speech recognition (ASR) system

• The goal is the lexical content of the human voice is converted to a computer-readable input

• Attempt to identify or confirm issue voice speaker rather than the content of the terms contained therein

Introduction

• Automatic speech recognition (ASR) system • Acoustics feature• Signal processing and feature extraction• Mel frequency cepstral coefficients (MFCC)

• Acoustics model• Statistically speech model• Gaussian mixture model (GMM)

MFCC

• Mel frequency cepstral coefficients (MFCC)

• MFCC takes human perception sensitivity with respect to frequencies into consideration, and therefore are best for speech/speaker recognition.

MFCC

1.Pre-emphasis

• The speech signal s(n) is sent to a high-pass filter

2.Frame blocking

3.Hamming windowing

• Each frame has to be multiplied with a hamming window in order to keep the continuity of the first and the last points in the frame

MFCC

4. Fast Fourier Transform or FFT

• The time domain signal into a frequency domain

5.Triangular Bandpass Filters

• Smooth the magnitude spectrum such that the harmonics are flattened in order to obtain the envelop of the spectrum with harmonics.

6.Discrete cosine transform or DCT

MFCC

7.Log energy

• The energy within a frame is also an important feature that can be easily obtained

8.Delta cepstrum

• Actually used in speech recognition, we usually coupled differential cepstrum parameters to show the changes of the the cepstrum parameters of the time

2D-DCT

• 2D-DCT modeling

Polynomial surface

• Polynomial surface modeling

Polynomial surface

• Polynomial surface modeling

Polynomial surface

• Polynomial surface modeling

Polynomial surface

• Polynomial surface modeling

GMM

• Gaussian mixture model (GMM)

• Is an effective tool for data modeling and pattern classification

• Speaker acoustic characteristics for clustering, and then each group of acoustic characteristics described with a Gaussian density distribution

Databases

• Databases• Evaluated on two distinct datasets • American English continuous speech as provided

in the TIMIT database • Marathi words database specially created for the

purpose

Results

Conclusion

• A comparison of performance with published results on the same task revealed that the spectro-temporal feature systems tested in this work improve upon the best previous systems’ performances in terms of classification accuracies on the specified datasets.

The End