Effect of Adding Positional Information on Convolutional Neural Networks for End-to-End Speech Recognition.
Jinhwan ParkWonyong SungPublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- speech recognition
- positional information
- convolutional neural networks
- hidden markov models
- language model
- automatic speech recognition
- speech signal
- pattern recognition
- speech synthesis
- noisy environments
- congestion control
- speech recognizer
- speaker identification
- position information
- speech recognition systems
- speaker independent
- speech recognition technology
- computer vision
- wireless sensor networks
- multiscale