Towards Realizing Sign Language to Emotional Speech Conversion by Deep Learning

This paper proposes a framework of sign language to emotional speech conversion based on deep learning to solve communication disorders between people with language barriers and healthy people. We firstly trained a gesture recognition model and a facial expression recognition model by a deep convolutional generative adversarial network (DCGAN). Then we trained an emotional speech acoustic model with a hybrid long short-term memory (LSTM). We select the initials and the finals of Mandarin as the emotional speech synthesis units to train a speaker-independent average voice model (AVM). The speaker adaptation is applied to train a speaker-dependent hybrid LST-M model with one target speaker emotional corpus from AVM. Finally, we combine the gesture recognition model and facial expression recognition model with the emotional speech synthesis model to realize the sign language to emotional speech conversion. The experiments show that the recognition rate of gesture recognition is 93.96%, and the recognition rate of facial expression recognition in the CK+ database is 96.01%. The converted emotional speech not only has high quality but also can accurately express the facial expression.