Combining Multiple Acoustic Models in GMM Spaces for Robust Speech Recognition.
Byung Ok KangOh-Wook KwonPublished in: IEICE Trans. Inf. Syst. (2016)
Keyphrases
- speech recognition
- combining multiple
- acoustic models
- speaker identification
- noisy environments
- speaker independent
- speech recognizer
- automatic speech recognition
- hidden markov models
- language model
- speaker recognition
- pattern recognition
- speech signal
- gaussian mixture model
- mixture model
- n gram
- information retrieval
- bayesian networks