An HMM-based speech-to-video synthesizer.
Jay J. WilliamsAggelos K. KatsaggelosPublished in: IEEE Trans. Neural Networks (2002)
Keyphrases
- text to speech
- hidden markov models
- video sequences
- video data
- speech recognition
- multimedia
- real time
- video frames
- broadcast news
- real time video
- digital video
- video content
- audio video
- digital audio
- content based video retrieval
- speech signal
- speech synthesis
- video analysis
- video streams
- space time
- video images
- audio signals
- video database
- human actions
- multimedia data
- audio features
- video segmentation
- dynamic scenes
- online video
- human activities
- pattern recognition
- endpoint detection