Exploiting polynomial-fit histogram equalization and temporal average for robust speech recognition.
Shih-Hsiang LinYao-Ming YehBerlin ChenPublished in: INTERSPEECH (2006)
Keyphrases
- speech recognition
- histogram equalization
- noisy environments
- hidden markov models
- language model
- image enhancement
- automatic speech recognition
- speech synthesis
- pattern recognition
- speech recognizer
- speech signal
- speech recognition technology
- speech recognition systems
- speech processing
- contrast enhancement
- speech recognizers
- speaker identification
- gray scale
- gray level
- speaker dependent
- multiscale
- dynamic range
- information retrieval
- denoising
- image features
- multiresolution