A clustering based feature selection method in spectro-temporal domain for speech recognition.
Nafiseh EsfandianFarbod RazzaziAlireza BehradPublished in: Eng. Appl. Artif. Intell. (2012)
Keyphrases
- speech recognition
- temporal domain
- hidden markov models
- spatial and temporal
- language model
- spatial domain
- speech signal
- speech processing
- spatio temporal
- speech synthesis
- automatic speech recognition
- k means
- optical flow
- temporal information
- temporal consistency
- pattern recognition
- speech recognition systems
- speech recognition technology
- isolated word
- noisy environments
- speaker identification
- space time
- video sequences
- speaker dependent
- three dimensional
- denoising
- motion estimation
- image segmentation