Unsupervised Pre-Training for Vietnamese Automatic Speech Recognition in the HYKIST Project.
Khai Le-DucPublished in: CoRR (2023)
Keyphrases
- automatic speech recognition
- speech recognition
- discriminative training
- supervised learning
- speech signal
- conversational speech
- word error rate
- hidden markov models
- broadcast news
- acoustic models
- word recognition
- speech retrieval
- speech corpus
- recognition errors
- noisy environments
- spontaneous speech
- spoken words
- speech sounds
- acoustic features
- hybrid method
- semi supervised