On the temporal decorrelation of feature parameters for noise-robust speech recognition.
Ho-Young JungSoo-Young LeePublished in: IEEE Trans. Speech Audio Process. (2000)
Keyphrases
- speech recognition
- noisy environments
- hidden markov models
- automatic speech recognition
- speech signal
- language model
- speech synthesis
- speech understanding
- speech processing
- speaker identification
- cepstral coefficients
- noisy speech
- speech recognizer
- noise reduction
- background noise
- speech recognition technology
- speech enhancement
- digit recognition
- isolated word
- speech retrieval
- speaker independent
- information retrieval
- additive noise
- noise level
- expectation maximization
- speech recognizers
- machine learning
- linear prediction
- blind source separation
- maximum likelihood
- feature set