Macro-Block Dropout for Improved Regularization in Training End-to-End Speech Recognition Models.
Chanwoo KimSathish IndurtiJinhwan ParkWonyong SungPublished in: SLT (2022)
Keyphrases
- end to end
- speech recognition
- acoustic models
- language model
- probabilistic model
- speech synthesis
- hidden markov models
- automatic speech recognition
- speech signal
- congestion control
- isolated word
- speech recognition technology
- speech recognizer
- computer vision
- machine learning
- broadcast news
- quality assessment
- information retrieval