Speaker Adaptation in Sparse Subspace of Acoustic Models.
Yongwon JeongPublished in: IEICE Trans. Inf. Syst. (2013)
Keyphrases
- acoustic models
- speech recognition
- speaker adaptation
- speaker independent
- speech recognizer
- automatic speech recognition
- high dimensional
- hidden markov models
- speaker identification
- spoken language
- broadcast news
- digit recognition
- speech signal
- principal component analysis
- language model
- speech recognition systems
- pattern recognition
- noisy environments
- feature space
- machine learning
- video data
- maximum likelihood
- text classification
- discriminative training
- semi supervised
- feature extraction