Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech Recognition.
Abner HernandezPaula Andrea Pérez-ToroElmar NöthJuan Rafael Orozco-ArroyaveAndreas K. MaierSeung Hee YangPublished in: INTERSPEECH (2022)
Keyphrases
- speech recognition
- cross lingual
- language model
- language modeling
- speech signal
- automatic speech recognition
- speech synthesis
- language independent
- speech recognizer
- hidden markov models
- cross language
- machine translation
- speech recognition technology
- speech processing
- speech recognition systems
- speaker identification
- parallel corpus
- pattern recognition
- speaker independent
- speech recognizers
- noisy environments
- document clustering
- word segmentation
- n gram
- query translation
- speaker dependent
- probabilistic model
- semi supervised
- transfer learning
- retrieval model
- news articles
- query expansion
- machine translation system
- statistical machine translation
- neural network
- isolated word