Deep-FSMN for Large Vocabulary Continuous Speech RecognitionShiliang Zhang, Li-Rong Dai, Ming Lei et al.|Unknown|2018Cited by 128
A hierarchical F0 modeling method for HMM-based speech synthesisMing Lei, Li-Rong Dai, Frank K. Soong et al.|Unknown|2010Cited by 25
Modeling F0 trajectories in hierarchically structured deep neural networksXiang Yin, Li-Rong Dai, Frank K. Soong et al.|Speech Communication|2015Cited by 23
An Effective Deep Embedding Learning Method Based on Dense-Residual Networks for Speaker VerificationYing Liu, Li-Rong Dai, Yan Song et al.|Unknown|2021Cited by 15
Deep-FSMN for Large Vocabulary Continuous Speech RecognitionShiliang Zhang, Li-Rong Dai, Ming Lei et al.|arXiv (Cornell University)|2018Cited by 13