An Improved Wav2Vec 2.0 Pre-Training Approach Using Enhanced Local Dependency Modeling for Speech Recognition.
Qiu-Shi ZhuJie ZhangMing-Hui WuXin FangLi-Rong DaiPublished in: Interspeech (2021)
Keyphrases
- speech recognition
- wall street journal corpus
- speech processing
- isolated word
- hidden markov models
- speech signal
- language model
- speech recognizer
- acoustic models
- automatic speech recognition
- speaker identification
- speech understanding
- pattern recognition
- speech recognition technology
- speech synthesis
- speech recognition systems
- speech recognizers
- noisy environments
- keyword spotting
- feature extraction
- data mining
- speaker recognition
- training set