Structured Pruning of Self-Supervised Pre-Trained Models for Speech Recognition and Understanding.
Yifan PengKwangyoun KimFelix WuPrashant SridharShinji WatanabePublished in: ICASSP (2023)
Keyphrases
- speech recognition
- hidden markov models
- pre trained
- speech processing
- acoustic models
- speech synthesis
- speech recognition technology
- pattern recognition
- noisy environments
- data sets
- automatic speech recognition
- speech signal
- language model
- probabilistic model
- speech recognizer
- speech recognition systems
- training data
- speaker identification
- speaker independent
- data mining