Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models.
Haoyu WangWei-Qiang ZhangHongbin SuoYulong WanPublished in: ISCSLP (2022)
Keyphrases
- speech recognition
- acoustic models
- pre trained
- speech recognizer
- speaker independent
- hidden markov models
- training data
- language model
- automatic speech recognition
- training examples
- speech signal
- pattern recognition
- noisy environments
- cross lingual
- speech recognition systems
- cross language information retrieval
- probabilistic model
- language independent
- broadcast news
- multi modal
- natural language