CTC Blank Triggered Dynamic Layer-Skipping for Efficient Ctc-Based Speech Recognition.
Junfeng HouPeiyao WangJincheng ZhangMeng YangMinwei FengJingcheng YinPublished in: ASRU (2023)
Keyphrases
- speech recognition
- speech synthesis
- hidden markov models
- automatic speech recognition
- speech understanding
- language model
- speech signal
- noisy environments
- speech recognition technology
- speech recognizer
- speech recognizers
- speaker identification
- speech processing
- pattern recognition
- speech retrieval
- handwriting recognition
- speaker independent
- non stationary
- feature space
- training data