Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea;
Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea;
Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea;
Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea;
Speech recognition; Decoding; Random access memory; Cats; Training; Acoustics; Computational modeling;
机译:桥接自动语音识别和心理语言学:将候选清单扩展到人类语音识别的端到端模型(L)
机译:使用公路连接启用深度较小的LSTM-RNN进行语音识别
机译:使用高速公路连接启用深度较小的LSTM-RNN进行语音识别?
机译:具有多步行RNN的设备端到端语音识别
机译:对话的端到端语音识别
机译:用BPE-ropout进行动态声学单元增强用于低资源端到端语音识别
机译:对设备的综述完全神经元端到端自动语音识别算法