Age-VOX-Celeb: Multi-Modal Corpus for Facial and Speech Estimation.
Naohiro TawaraAtsunori OgawaYuki KitagishiHosana KamiyamaPublished in: ICASSP (2021)
Keyphrases
- multi modal
- audio visual
- age estimation
- emotion recognition
- estimation accuracy
- spontaneous speech
- high dimensional
- facial expressions
- speech recognition
- human faces
- face images
- facial images
- facial animation
- multi modality
- face recognition
- speech signal
- semantic concepts
- image annotation
- cross modal
- humanoid robot
- feature selection
- fusing multiple