Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/46812
Title: Speech Enhancement for next generation human computer interfaces
Authors: Talal Bin Amin
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2010
Abstract: In recent years we have seen a lot of growth of speech recognition systems employed in commercial applications. Current Automatic Speech Recognition (ASR) and Interactive Voice Response (IVR) systems are limited in performance as they can only function with particular accuracy in certain noise free/high SNR environment. Although much attention has been paid to speech enhancement techniques for the human ear but the idea is fairly new in terms of machines. Noise whether stationary or non-stationary is the main hurdle in the commercial success of ASR systems as it severely degrades their performance in terms of recognition accuracy and also limits the environment in which they can be used. A good example is modern mobile phones which have the feature of ASR in them but most people do not use it as it does not recognize the spoken utterances correctly while travelling in cars, at airports or other noisy environments.
Description: 51 p.
URI: http://hdl.handle.net/10356/46812
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
EEE_THESES_157.pdf
  Restricted Access
6.59 MBAdobe PDFView/Open

Page view(s) 50

212
Updated on Nov 25, 2020

Download(s) 50

10
Updated on Nov 25, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.