Lightweight End-to-End Speech Recognition from Raw Audio Data Using Sinc-Convolutions.
Ludwig KürzingerNicolas LindaePalle KlewitzGerhard RigollPublished in: INTERSPEECH (2020)
Keyphrases
- lightweight
- end to end
- speech recognition
- hidden markov models
- speech signal
- language model
- automatic speech recognition
- pattern recognition
- speech synthesis
- speech recognizer
- speech recognition systems
- multipath
- speech processing
- congestion control
- speech recognition technology
- ad hoc networks
- speaker dependent
- speaker identification
- multimedia
- application layer
- noisy environments
- multi hop
- wireless sensor networks
- speaker independent
- image processing