Discriminative splitting of Gaussian/log-linear mixture HMMs for speech recognition.
Muhammad Ali TahirRalf SchlüterHermann NeyPublished in: ASRU (2011)
Keyphrases
- speech recognition
- log linear
- discriminative training
- hidden markov models
- log linear models
- mixture model
- automatic speech recognition
- gaussian mixture model
- gaussian distribution
- maximum likelihood
- language model
- speech signal
- speaker identification
- expectation maximization
- conditional random fields
- pattern recognition
- speech recognition systems
- speech recognizer
- em algorithm
- acoustic models
- probabilistic model
- support vector machine
- probabilistic interpretation
- word recognition
- generative model