4 papers
Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition
Ye Bai, Jie Li, Wenjing Han +5
While transformers and their variant conformers show promising performance in speech recognition, the parameterized property leads to much memory cost during training and inference…
Speaker-aware speech-transformer
Zhiyun Fan, Jie Li, Shiyu Zhou +1
Recently, end-to-end (E2E) models become a competitive alternative to the conventional hybrid automatic speech recognition (ASR) systems. However, they still suffer from speaker mi…
Improving Gated Recurrent Unit Based Acoustic Modeling with Batch Normalization and Enlarged Context
Jie Li, Yahui Shan, Xiaorui Wang +1
The use of future contextual information is typically shown to be helpful for acoustic modeling. Recently, we proposed a RNN model called minimal gated recurrent unit with input pr…
Gated Recurrent Unit Based Acoustic Modeling with Future Context
Jie Li, Xiaorui Wang, Yuanyuan Zhao +1
The use of future contextual information is typically shown to be helpful for acoustic modeling. However, for the recurrent neural network (RNN), it's not so easy to model the futu…