Titlebook: Distributed Computing and Artificial Intelligence, 17th International Conference; Yucheng Dong,Enrique Herrera-Viedma,Sara Rodríguez Confe

堅(jiān)毅

松馳

Mobile Device-Based Speech Enhancement System Using Lip-Reading,sing the VAE encoder and CNN was performed with 20 Japanese words. The experimental result showed 65% recognition accuracy, and 100% including 1. and 2. candidates. The lip-reading type speech enhancement seems appropriate for embedding mobile devices in consideration of both usability and small voc