Knowledge Distillation For CTC-based Speech Recognition Via Consistent Acoustic Representation Learning.
Sanli TianKeqi DengZehan LiLingxuan YeGaofeng ChengTa LiYonghong YanPublished in: INTERSPEECH (2022)
Keyphrases
- speech recognition
- hidden markov models
- learning process
- speech recognition systems
- image processing
- pattern recognition
- knowledge representation
- language model
- speech signal
- speech processing
- speech synthesis
- speech recognizer
- feature extraction
- automatic speech recognition
- speaker identification
- neural network
- speaker independent