Residual-guided Personalized Speech Synthesis based on Face Image.
Jianrong WangZixuan WangXiaosheng HuXuewei LiQiang FangLi LiuPublished in: CoRR (2022)
Keyphrases
- speech synthesis
- face images
- face recognition
- speech recognition
- text to speech
- human faces
- input image
- feature vectors
- principal component analysis
- facial expressions
- facial features
- low resolution
- face representation and recognition
- face verification
- illumination variations
- face databases
- low resolution face images
- training set
- feature extraction
- face recognition systems
- face recognition algorithms
- high resolution
- cmu pie
- human face recognition
- age estimation
- feature points
- pose variations
- real time
- information retrieval
- recognizing faces
- machine learning
- data sets
- recognition rate
- feature space
- pattern recognition
- image sequences
- computer vision
- neural network