Full metadata record
DC FieldValueLanguage
dc.contributorDepartment of Electronic and Information Engineeringen_US
dc.contributor.advisorChi, Zheru (EIE)-
dc.creatorGao Wuhang-
dc.publisherHong Kong Polytechnic University-
dc.rightsAll rights reserveden_US
dc.titleUser-dependent voice dialling on smartphonesen_US
dcterms.abstractSpeech recognition is a hot topic in machine intelligence. One important application of speech recognition is for human computer interaction by "talking to machines". It has been a technology frequently portrayed in science fiction films. However, due to the complexity of the problem, speech recognition technology is still not very mature in practice. Cloud based speech recognition is a promising way to handle this task. In this dissertation, we report the development of a voice dialling system for smart phones. The user of a smartphone can dial a number by reading out the name of the person to be phoned. In this dissertation, speech recognition techniques are first reviewed. Most existing speech recognition algorithms have been found not suitable for mobile devices due to very high computational complexity. In our investigation, we use Core Audio Format (CAF) format to record voices, use Mel-Frequency Cepstral Coefficient (MFCC) to extract the eigenvectors of speech signal. Based on Dynamic Time Warping (DTW), we propose a DTW based linear comparison algorithm to perform user-dependent voice dialling on smartphones. The user of a smartphone first stores speech samples. The signal processing and feature extraction are carried out after the data are collected. The application works locally without a server so the network speed and safety are not issues. Also this application is language independent. The voice matching rate is highly related to the quality of samples. The performance of this application is evaluated on IOS simulator and IPhone4s. The application can achieve a correct matching rate of 88%.en_US
dcterms.extent40 leaves : illustrations ; 30 cmen_US
dcterms.isPartOfPolyU Electronic Thesesen_US
dcterms.educationalLevelAll Masteren_US
dcterms.LCSHMobile computing.en_US
dcterms.LCSHAutomatic speech recognition.en_US
dcterms.LCSHSpeech processing systems.en_US
dcterms.LCSHHong Kong Polytechnic University -- Dissertationsen_US
dcterms.accessRightsrestricted accessen_US

Files in This Item:
File Description SizeFormat 
b28194810.pdfFor All Users (off-campus access for PolyU Staff & Students only)1.55 MBAdobe PDFView/Open

Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. 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.
  3. 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.

Show simple item record

Please use this identifier to cite or link to this item: https://theses.lib.polyu.edu.hk/handle/200/8143