Improving the noise-robustness of mel-frequency cepstral coefficients for speech processing.
Sourabh RavindranDavid V. AndersonMalcolm SlaneyPublished in: SAPA@INTERSPEECH (2006)
Keyphrases
- speech processing
- speaker identification
- noisy environments
- speech recognition
- speaker recognition
- gaussian mixture model
- speech signal
- noise reduction
- language identification
- feature extraction
- signal processing
- broadcast news
- multimedia systems
- natural language processing
- signal to noise ratio
- machine learning
- neural network
- feature vectors
- feature space
- english text
- mixture model
- hidden markov models