Dysarthric Speech Recognition using Depthwise Separable Convolutions: Preliminary Study.
Seyed Reza ShahamiriKrishnendu MandalSudeshna SarkarPublished in: SpeD (2023)
Keyphrases
- preliminary study
- speech recognition
- speech signal
- fourier transform
- automatic speech recognition
- speech synthesis
- recognition engine
- text to speech
- audio visual
- spoken language
- neural network
- dialogue system
- signal processing
- broadcast news
- spoken dialogue systems
- speaker recognition
- speech processing
- user interface
- image processing
- real time
- speech corpus
- endpoint detection