Label-Driven Time-Frequency Masking for Robust Speech Command Recognition.
Meet H. SoniImran SheikhSunil Kumar KopparapuPublished in: TSD (2019)
Keyphrases
- recognition engine
- noisy environments
- partial occlusion
- speech recognition
- varying illumination conditions
- data driven
- recognition accuracy
- pattern recognition
- object recognition
- pose invariant face recognition
- feature extraction
- robust recognition
- continuous speech recognition
- recognition process
- image recognition
- activity recognition
- multi label
- recognition rate
- recognition algorithm
- human visual system
- audio visual
- speech signal
- automatic recognition
- illumination invariance
- face recognition
- automatic speech recognition systems
- digit recognition
- speech synthesis
- dialogue system
- character recognition
- action recognition
- signal processing
- multiscale