Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition.
Xuefei WangYanhua LongYijie LiHaoran WeiPublished in: INTERSPEECH (2023)
Keyphrases
- end to end
- speech recognition
- information fusion
- wall street journal corpus
- multi source
- isolated word
- data fusion
- hidden markov models
- automatic speech recognition
- acoustic models
- language model
- speech recognizer
- pattern recognition
- noisy environments
- soft computing
- speech recognition technology
- speech synthesis
- speech signal
- congestion control
- speaker identification
- speech recognition systems
- speaker independent
- resource management
- fuzzy logic
- machine learning
- neural network
- discriminative training
- probabilistic model
- artificial neural networks
- video sequences