Dynamic Acoustic Unit Augmentation with BPE-Dropout for Low-Resource End-to-End Speech Recognition.
Aleksandr LaptevAndrei AndrusenkoIvan PodluzhnyAnton MitrofanovIvan MedennikovYuri MatveevPublished in: Sensors (2021)
Keyphrases
- end to end
- speech recognition
- speech recognition systems
- speaker independent
- speech recognizers
- speech recognizer
- language model
- hidden markov models
- speech synthesis
- speech signal
- pattern recognition
- congestion control
- acoustic models
- noisy speech
- noisy environments
- speech processing
- speaker dependent
- speech recognition technology
- automatic speech recognition
- isolated word
- speaker identification
- computer vision
- speaker adaptation