Phonation types and decoders' gender influence the recognition of Mandarin emotional speech.

What is it about?

This study elucidated the roles of phonation types and the decoders’ gender in Mandarin emotional speech recognition using the technique of articulatory speech synthesis. Specifically, the phonation types contained breathy, modal, and pressed voices, and the emotional categories included five emotions such as happiness, anger, fear, sadness, and neutrality. It is concluded that pressed voice is closely related to the recognition of anger and breathy voice to the recognition of fear, while the recognition of sadness and happiness does not rely on phonation types to a great degree. Concerning gender differences, females outperformed males in recognizing fear with different phonation types. Females connected modal to pressed voice with neutrality while males linked modal voice to neutrality.

Featured Image

Photo by Alexas_Fotos on Unsplash

Photo by Alexas_Fotos on Unsplash

Why is it important?

This is the first study to investigate the roles of phonation types and the decoders’ gender in the recognition of Mandarin emotional speech by means of articulatory speech synthesis. This study provides further evidence that phonation types play a crucial role in the recognition of emotional speech and that gender differences exist. The findings of this study are likely to be helpful to synthesize speech and promote robust automatic recognition of emotional speech. Furthermore, the findings of this study might have implications for diagnosis and intervention among clinical populations with hearing impairment or gender-related psychiatric disorders.

Perspectives