Complementary Gaussian Mixture Models for Multimodal Speech Recognition.
Gonzalo D. SadLucas D. TerissiJuan Carlos GómezPublished in: MPRSS (2014)
Keyphrases
- gaussian mixture model
- speech recognition
- speaker identification
- speaker recognition
- mixture model
- language model
- em algorithm
- hidden markov models
- multi modal
- speech signal
- expectation maximization
- maximum likelihood
- automatic speech recognition
- speech recognizer
- mel frequency cepstral coefficients
- feature vectors
- speech synthesis
- pattern recognition
- speech recognition technology
- probability density function
- speech recognition systems
- noisy environments
- speaker independent
- gaussian distribution
- feature space
- probabilistic neural network
- audio visual
- neural network
- probabilistic model
- information retrieval