Extension and further analysis of higher order cepstral moment normalization (HOCMN) for robust features in speech recognition.
Chang-Wen HsuLin-Shan LeePublished in: INTERSPEECH (2006)
Keyphrases
- speech recognition
- hidden markov models
- higher order
- pattern recognition
- noisy environments
- language model
- automatic speech recognition
- speech recognition systems
- speech synthesis
- cepstral coefficients
- speech signal
- isolated word
- speech recognition technology
- speech understanding
- speech recognizer
- speech processing
- speaker identification
- low level
- keyword spotting
- neural network
- feature vectors
- speech recognition errors
- face recognition