iRepository at Perpustakaan UniMAP >
The Library >
Conference Papers >
Please use this identifier to cite or link to this item:
|Title: ||Overview of automatic stuttering recognition system|
|Authors: ||Lim, Sin Chee|
Ooi, Chia Ai
|Keywords: ||Stuttering;Speech disorders;Stuttering recognition system;Stuttering recognition system -- Design and construction;Neural networks (Computer science)|
|Issue Date: ||11-Oct-2009|
|Publisher: ||Universiti Malaysia Perlis|
|Citation: ||p.5B7 1 - 5B7 6|
|Series/Report no.: ||Proceedings of the International Conference on Man-Machine Systems (ICoMMS 2009)|
|Abstract: ||Stuttering is a speech disorder. The flow of speech is disrupted by involuntary repetitions and prolongation of sounds,
syllables, words or phrases, and involuntary silent pauses or blocks in communication. Stuttering is an interest subject of
researchers from many various domains such as speech physiology & pathology, psychology, acoustic and signal analysis.
Thus there are many researchers have been done previously. This paper presents an overview of previous works on automatic
stuttering recognition system. Normally, classification of speech disorder is difficult and complicated. However some classification techniques associated with stuttering are commonly recognized. This paper review on classification techniques are utilized in automatic stuttering recognition for evaluating speech problem
for stutterers. Some previous works discussed the different steps involved in recognizing stuttered speech from speech samples. This paper compares different classification techniques proposed by previous researchers. Classification techniques used in previous works are Artificial Neural Networks (ANNs), Hidden
Markov Model (HMM) and Support Vector Machine (SVM).|
|Description: ||Organized by School of Mechatronic Engineering (UniMAP) & co-organized by The Institution of Engineering Malaysia (IEM), 11th - 13th October 2009 at Batu Feringhi, Penang, Malaysia.|
|Appears in Collections:||Conference Papers|
Sazali Yaacob, Prof. Dr.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.