Speech production based on the mel-frequency cepstral coefficients.
Zbynek TychtlJosef PsutkaPublished in: EUROSPEECH (1999)
Keyphrases
- mel frequency cepstral coefficients
- speech signal
- speaker recognition
- speaker identification
- acoustic features
- linear predictive
- speech recognition
- gaussian mixture model
- feature set
- spectral features
- feature vectors
- speaker verification
- cepstral coefficients
- automatic speech recognition
- audio features
- speaker diarization
- principal component analysis
- extracting features
- feature extraction
- broadcast news
- vector quantization
- language model
- noisy environments
- language identification
- probabilistic neural network
- mixture model
- visual features
- hidden markov models
- music information retrieval
- linear prediction
- non stationary
- pattern recognition
- model selection
- audio visual
- multi modal
- low level
- training set
- training data
- machine learning