Vector quantization with memory and multi-labeling for isolated video-only automatic speech recognition.
Louis H. TerryDerek J. ShiellAggelos K. KatsaggelosPublished in: ICIP (2008)
Keyphrases
- vector quantization
- automatic speech recognition
- broadcast news
- speech recognition
- image compression
- joint source and channel coding
- vector quantizer
- speech signal
- conversational speech
- hidden markov models
- video data
- multimedia
- reduced complexity
- distortion measure
- video sequences
- video content
- video frames
- finite state vector quantization
- fractal image compression
- unsupervised learning
- noisy environments
- video retrieval
- video streams
- image quality
- feature extraction
- image sequences
- image segmentation
- machine learning