Spectrum enhancement with sparse coding for robust speech recognition.
Yongjun HeGuanglu SunJiqing HanPublished in: Digit. Signal Process. (2015)
Keyphrases
- speech recognition
- sparse coding
- dictionary learning
- noisy environments
- sparse representation
- natural images
- language model
- linear combination
- hidden markov models
- automatic speech recognition
- image classification
- speech synthesis
- image representation
- speech recognizer
- pattern recognition
- unsupervised learning
- generative model
- speech recognition systems
- multiscale
- speech signal
- image patches
- visual words
- speaker identification
- feature space
- image processing
- high dimensional