Multi-Task Multi-Resolution Char-to-BPE Cross-Attention Decoder for End-to-End Speech Recognition.
Dhananjaya GowdaAbhinav GargKwangyoun KimMehul KumarChanwoo KimPublished in: INTERSPEECH (2019)
Keyphrases
- end to end
- speech recognition
- multi task
- multiresolution
- learning tasks
- language model
- hidden markov models
- learning problems
- feature selection
- pattern recognition
- transfer learning
- multi class
- speech recognition systems
- wavelet transform
- neural network
- information gain
- probabilistic model
- training data
- computer vision
- learning algorithm
- machine learning