The following publications are possibly variants of this publication:
- B&Anet: Combining bidirectional LSTM and self-attention for end-to-end learning of task-oriented dialogue systemQun He, Wenjing Liu, Cai Zhangli. speech, 125:15-23, 2020. [doi]
- Deep Attention Gated Dilated Temporal Convolutional Networks with Intra-Parallel Convolutional Modules for End-to-End Monaural Speech SeparationZiqiang Shi, Huibin Lin, Liu Liu, Rujie Liu, Jiqing Han, Anyan Shi. interspeech 2019: 3183-3187 [doi]
- Learning deep multimodal affective features for spontaneous speech emotion recognitionShiqing Zhang, Xin Tao, Yuelong Chuang, Xiaoming Zhao. speech, 127:73-81, 2021. [doi]