Author: | Kwan, Ka-keung |
Title: | Interactive voice response system for creation of linguistic database |
Degree: | M.Sc. |
Year: | 2000 |
Subject: | Automatic speech recognition Speech processing systems Hong Kong Polytechnic University -- Dissertations |
Department: | Multi-disciplinary Studies Department of Electronic and Information Engineering |
Pages: | vi, 64 leaves : ill. ; 30 cm. + 1 computer optical disc |
Language: | English |
Abstract: | Speech recognition is an important area of research today because of current trends in user interfaces. Most speech recognition systems are based on observing the statistics of speech data in a training data set and generalising it to a test data set. Hence, this kind of research requires a large amount of speech data. However, human language is so complex and information-rich, computer software for speech recognition must be fed with enormous amounts of varied linguistic data, i.e. speech, text, lexicons, and grammars, in order the system performance can be robust and effective. It is very difficult to collect and organise such large amount of data manually. This project provides a solution of using the Interactive Voice Response System (IVRS) to create the required database. For instance, call a specified number, output a specified tone onto the phone line, record the audio data received on the phone line on the host computer and generate a voice database. In this report, we will see how to use a computer with a Dialogic Card D/21H and a Call Processing Application to set-up an IVRS so as to create a Cantonese speech corpus (Cantonese speech database). |
Rights: | All rights reserved |
Access: | restricted access |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
b15276077.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 2.98 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/3683