A real-time super-resolution robot audition system that improves the robustness of simultaneous speech recognition.
Keisuke NakamuraKazuhiro NakadaiHiroshi G. OkunoPublished in: Adv. Robotics (2013)
Keyphrases
- speech recognition
- super resolution
- low resolution
- high resolution
- low resolution images
- image restoration
- hidden markov models
- automatic speech recognition
- resolution enhancement
- super resolved
- motion blur
- high quality
- speech synthesis
- image super resolution
- language model
- multi frame
- super resolution reconstruction
- motion estimation
- speech recognition systems
- speech signal
- high resolution images
- speaker identification
- speech recognizer
- depth map
- pattern recognition
- image processing
- image patches
- input image