Recognition of Listener's Nodding by LSTM Based on Movement of Facial Keypoints and Speech Intonation.
Takayoshi YamashitaMaya NakagawaHironobu FujiyoshiYuji HaikawaPublished in: HCI (34) (2019)
Keyphrases
- keypoints
- object recognition
- keypoint detection
- image matching
- pose variations
- recognition engine
- scale invariant
- text to speech
- face recognition
- emotion recognition
- facial expression recognition
- speech recognition
- multiscale
- keypoint matching
- pattern recognition
- image features
- feature detection
- synthesized speech
- prosodic features
- scale invariant feature transform
- sift descriptors
- facial expressions
- computer vision
- facial images
- scale space
- invariant features
- sift features
- visual words
- feature extraction
- speech signal
- natural images
- noisy environments
- speech synthesis
- scale invariant features
- face images
- hidden markov models
- object detection
- human faces