Scale-Space and Edge Detection Using Anisotropic Diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Task-Specific Contour Tracker for Ultrasound
MMBIA '00 Proceedings of the IEEE Workshop on Mathematical Methods in Biomedical Image Analysis
A tissue-conductive acoustic sensor applied in speech recognition for privacy
Proceedings of the 2005 joint conference on Smart objects and ambient intelligence: innovative context-aware services: usages and technologies
Asynchrony modeling for audio-visual speech recognition
HLT '02 Proceedings of the second international conference on Human Language Technology Research
Speckle reducing anisotropic diffusion
IEEE Transactions on Image Processing
Speech Communication
ICCHP keynote: recognizing silent and weak speech based on electromyography
ICCHP'10 Proceedings of the 12th international conference on Computers helping people with special needs: Part I
Emerging Input Technologies for Always-Available Mobile Interaction
Foundations and Trends in Human-Computer Interaction
A tongue training system for children with down syndrome
Proceedings of the 26th annual ACM symposium on User interface software and technology
Hi-index | 0.00 |
This article presents a segmental vocoder driven by ultrasound and optical images (standard CCD camera) of the tongue and lips for a ''silent speech interface'' application, usable either by a laryngectomized patient or for silent communication. The system is built around an audio-visual dictionary which associates visual to acoustic observations for each phonetic class. Visual features are extracted from ultrasound images of the tongue and from video images of the lips using a PCA-based image coding technique. Visual observations of each phonetic class are modeled by continuous HMMs. The system then combines a phone recognition stage with corpus-based synthesis. In the recognition stage, the visual HMMs are used to identify phonetic targets in a sequence of visual features. In the synthesis stage, these phonetic targets constrain the dictionary search for the sequence of diphones that maximizes similarity to the input test data in the visual space, subject to a concatenation cost in the acoustic domain. A prosody-template is extracted from the training corpus, and the final speech waveform is generated using ''Harmonic plus Noise Model'' concatenative synthesis techniques. Experimental results are based on an audiovisual database containing 1h of continuous speech from each of two speakers.