Utterance-Based Selective Training for the Automatic Creation of Task-Dependent Acoustic Models.
Tobias CincarekTomoki TodaHiroshi SaruwatariKiyohiro ShikanoPublished in: IEICE Trans. Inf. Syst. (2006)
Keyphrases
- acoustic models
- speech recognition
- speech recognizer
- hidden markov models
- automatic speech recognition
- speaker independent
- spoken language
- training process
- broadcast news
- supervised learning
- multi modal
- discriminative training
- speaker identification
- speech signal
- noisy environments
- data sets
- training set
- pattern recognition
- image processing