Generalized mel frequency cepstral coefficients for large-vocabulary speaker-independent continuous-speech recognition.
Rivarol VerginDouglas D. O'ShaughnessyAzarshid FarhatPublished in: IEEE Trans. Speech Audio Process. (1999)
Keyphrases
- continuous speech recognition
- speaker identification
- speaker independent
- mel frequency cepstral coefficients
- speech recognition
- speaker dependent
- speech signal
- gaussian mixture model
- speaker recognition
- speech recognition systems
- noisy environments
- hidden markov models
- feature extraction
- speaker adaptation
- feature vectors
- probabilistic neural network
- broadcast news
- acoustic features
- automatic speech recognition
- language model
- feature set
- speech recognizer
- speaker diarization
- mixture model
- expectation maximization
- principal component analysis