1. aidatatang200zh, ., a free Chinese Mandarin speech corpus by Beijing DataTang Technology, in: https://www.datatang.com.
2. Deep speech 2: End-to-end speech recognition in english and mandarin;Amodei,2016
3. An end-to-end multimodal voice activity detection using wavenet encoder and residual networks;Ariav;IEEE J. Sel. Top. Sign. Proces.,2019
4. Barras, B., SoX: Sound eXchange. Technical Report.
5. Curriculum learning;Bengio,2009