Histogram equalization and noise masking for robust speech recognition.
Xueru ZhangKris DemuynckHugo Van hammePublished in: ICASSP (2010)
Keyphrases
- speech recognition
- noisy environments
- histogram equalization
- hidden markov models
- image enhancement
- speech signal
- automatic speech recognition
- language model
- speech processing
- speaker identification
- pattern recognition
- noise reduction
- gray scale
- background noise
- speech recognizer
- image contrast
- speech recognition systems
- noisy speech
- speech synthesis
- contrast enhancement
- speech recognition technology
- machine learning
- color images
- image contrast enhancement
- image processing
- dynamic range
- visual quality
- image database
- image analysis
- image segmentation
- speaker independent
- neural network
- isolated word