Two-stage model-based feature compensation for robust speech recognition.
Haifeng ShenGang LiuJun GuoPublished in: Computing (2012)
Keyphrases
- speech recognition
- noisy environments
- language model
- cepstral coefficients
- hidden markov models
- automatic speech recognition
- speech recognizer
- speech synthesis
- speech processing
- speech understanding
- speech recognition systems
- pattern recognition
- speech signal
- speech recognition technology
- speech recognizers
- handwriting recognition
- speaker identification
- speech retrieval
- speaker recognition
- keyword spotting
- information retrieval
- n gram
- speaker dependent
- feature vectors
- mobile devices
- image processing