Time-Frequency Correlation-Based Missing-Feature Reconstruction for Robust Speech Recognition in Band-Restricted Conditions.
Wooil KimJohn H. L. HansenPublished in: IEEE Trans. Speech Audio Process. (2009)
Keyphrases
- speech recognition
- noisy environments
- language model
- hidden markov models
- speech signal
- automatic speech recognition
- speech processing
- speech synthesis
- speech understanding
- pattern recognition
- speaker identification
- cepstral coefficients
- speech recognition technology
- speech recognition systems
- speech recognizer
- feature vectors
- speaker dependent
- speech recognition errors
- speech recognizers
- keyword spotting
- speaker recognition