FiliText: A Filipino hands-free text messaging application

Date of Publication

2011

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Computer Science

College

College of Computer Studies

Department/Unit

Computer Science

Thesis Adviser

Danny Cheng

Defense Panel Member

Allan Borra

Clement Ong

Abstract/Summary

This research describes the ways that were employed to create a hands free text messaging application of recognizing the Filipino language which will allow users to send text messages using speech. It tackles the problem of having drivers use their hand phones for texting while driving. This application is currently developed on desktop computers to serve as a stepping stone for future development to further study on Filipino speech recognition and its application to Filipino text messaging. It uses Sphinx-4 as its back end and the UP-Diliman Filipino Speech Corpus for the training data. SphinxTrain is used for training the acoustic model and the language model. It also allows the user to convert the output generated to its text speak equivalent since Filipinos no longer use proper spelling in text messaging. With proper use of speech, an overall word accuracy rate of 85.13% is attained and 73.44% for sentence understandability.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU19858

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

109, 7, 13 unnumbered leaves ; 28 cm.

Keywords

Text messaging (Cell phone systems)

This document is currently not available here.

Share

COinS