FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition.
Szu-Jui ChenJiamin XieJohn H. L. HansenPublished in: INTERSPEECH (2022)
Keyphrases
- end to end
- speech recognition
- pattern recognition
- feature set
- hidden markov models
- cepstral coefficients
- language model
- speech signal
- feature vectors
- classification accuracy
- automatic speech recognition
- noisy environments
- speech recognition systems
- speech synthesis
- feature space
- feature extraction
- word processing
- computer based instruction
- computer vision