• Publications
  • Influence
An adaptive edge detection based colorization algorithm and its applications
TLDR
We introduce a general and fast colorization methodology with the aid of an adaptive edge detection scheme, which may prevent the colorization process from bleeding over object boundaries. Expand
  • 126
  • 4
  • PDF
Hierarchical prosodic pattern selection based on Fujisaki model for natural mandarin speech synthesis
TLDR
In this paper, a novel hierarchical prosodic unit selection method is proposed based on pitch contour pattern retrieval, in order to obtained natural pitch contours of the personalized synthetic voice. Expand
  • 7
  • 2
Personalized Spectral and Prosody Conversion Using Frame-Based Codeword Distribution and Adaptive CRF
TLDR
This study proposes a voice conversion-based approach to personalized text-to-speech synthesis, based on distribution-based alignment and prosodic word boundary detection, can improve the speech quality and speaker similarity of the converted speech. Expand
  • 21
  • 1
HMM-based Mandarin Singing Voice Synthesis Using Tailored Synthesis Units and Question Sets
TLDR
The Hidden Markov Model-based synthesis approach is employed in this study to construct a Mandarin singing voice synthesis system based on tailored synthesis units and a question set. Expand
  • 4
  • 1
  • PDF
Polyglot Speech Synthesis Based on Cross-Lingual Frame Selection Using Auditory and Articulatory Features
TLDR
In this paper, an approach for polyglot speech synthesis based on cross-lingual frame selection is proposed. Expand
  • 12
Cross-lingual frame selection method for polyglot speech synthesis
TLDR
A novel approach is proposed to creating a polyglot speech synthesis system without the need of collecting speech data from a bilingual (or multilingual) speaker, which is often expensive or infeasible. Expand
  • 8
  • PDF
Personalized natural speech synthesis based on retrieval of pitch patterns using hierarchical Fujisaki model
TLDR
An approach to retrieval of personalized pitch patterns from the real speech corpus of the target speaker, incorporating with the HMM-based speech synthesizer, to generate a personalized natural pitch contour. Expand
  • 6
Error-resilient MPEG-4 video communication over error-prone wireless networks
This work presents an error-resilient MPEG-4 video communication system. The system comprises an error-resilient encoder, an adaptive error-resilient transcoder, an error-resilient decoder and theExpand
  • 5
  • PDF
Design and implementation of an efficient MPEG-4 interactive terminal on embedded devices
TLDR
We present an efficient MPEG-4-based interactive player for PDA-like embedded devices in this paper. Expand
  • 4
  • PDF
A visual MPEG-4 scene editor
TLDR
We have implemented a visual MPEG-4 scene editor for creating 2D/3D mixed scenes, with the following features: event routing mechanism; visual editing; friendly user interface. Expand
  • 1
  • PDF
...
1
2
3
...