Speech/Speaker Recognition Using a HMM/GMM Hybrid Model.
M. Elena RodríguezBelén Ruíz-MezcuaÁngel García-CrespoFernando GarcíaPublished in: AVBPA (1997)
Keyphrases
- hybrid model
- speaker identification
- speech recognition
- speaker recognition
- speech signal
- hidden markov models
- speaker independent
- gaussian mixture model
- mel frequency cepstral coefficients
- automatic speech recognition systems
- automatic speech recognition
- speaker dependent
- artificial neural networks
- vocal tract
- noisy environments
- speech synthesis
- visual speech
- speaker verification
- voice activity detection
- broadcast news
- phoneme recognition
- probabilistic neural network
- audio visual
- speech recognizer
- hybrid models
- back propagation neural network
- support vector regression
- non stationary
- multi stream
- support vector machine svm
- language model
- speaker adaptation
- pattern recognition
- feature extraction
- speech recognition systems
- support vector machine
- mixture model
- neural network
- support vector