APSIPA Transactions on Signal and Information Processing > Vol 8 > Issue 1

Development of a computationally efficient voice conversion system on mobile phones

Shuhua Gao, National University of Singapore, Singapore, Xiaoling Wu, National University of Singapore, Singapore, Cheng Xiang, National University of Singapore, Singapore, Dongyan Huang, Institute for Infocomm Research, Singapore, huang@i2r.a-star.edu.sg
 
Suggested Citation
Shuhua Gao, Xiaoling Wu, Cheng Xiang and Dongyan Huang (2019), "Development of a computationally efficient voice conversion system on mobile phones", APSIPA Transactions on Signal and Information Processing: Vol. 8: No. 1, e4. http://dx.doi.org/10.1017/ATSIP.2018.23

Publication Date: 04 Jan 2019
© 2019 Shuhua Gao, Xiaoling Wu, Cheng Xiang and Dongyan Huang
 
Subjects
 
Keywords
Voice conversionGMMMobile applicationParallel computingWeighted frequency warping
 

Share

Open Access

This is published under the terms of the Creative Commons Attribution licence.

Downloaded: 1181 times

In this article:
I. INTRODUCTION 
II. VOICE CONVERSION FRAMEWORK 
III. EFFICIENT IMPLEMENTATION OF CORE ALGORITHMS 
IV. IOS APPLICATION DEVELOPMENT 
V. EXPERIMENTS AND RESULTS 
VI. DISCUSSION 
VII. CONCLUSION 

Abstract

Voice conversion aims to change a source speaker's voice to make it sound like the one of a target speaker while preserving linguistic information. Despite the rapid advance of voice conversion algorithms in the last decade, most of them are still too complicated to be accessible to the public. With the popularity of mobile devices especially smart phones, mobile voice conversion applications are highly desirable such that everyone can enjoy the pleasure of high-quality voice mimicry and people with speech disorders can also potentially benefit from it. Due to the limited computing resources on mobile phones, the major concern is the time efficiency of such a mobile application to guarantee positive user experience. In this paper, we detail the development of a mobile voice conversion system based on the Gaussian mixture model (GMM) and the weighted frequency warping methods. We attempt to boost the computational efficiency by making the best of hardware characteristics of today's mobile phones, such as parallel computing on multiple cores and the advanced vectorization support. Experimental evaluation results indicate that our system can achieve acceptable voice conversion performance while the conversion time for a five-second sentence only takes slightly more than one second on iPhone 7.

DOI:10.1017/ATSIP.2018.23