Boosting Cross-Domain Speech Recognition With Self-Supervision.
Han ZhuGaofeng ChengJindong WangWenxin HouPengyuan ZhangYonghong YanPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
- speech recognition
- cross domain
- hidden markov models
- sentiment classification
- automatic speech recognition
- transfer learning
- knowledge transfer
- speech recognizer
- text categorization
- speech signal
- speech recognition technology
- speech synthesis
- language model
- speech recognition systems
- learning algorithm
- pattern recognition
- noisy environments
- feature selection
- speaker identification
- speaker independent
- decision trees