The unified streaming and non-streaming speech recognition model has ach...
Recent researches indicate that utilizing the frequency information of i...
High-utility sequential pattern mining (HUSPM) has emerged as an importa...
For Automatic Speech Recognition (ASR), the CTC-based methods have becom...
The choice of modeling units affects the performance of the acoustic mod...
Dynamic attention mechanism and global modeling ability make Transformer...
Recent years have seen the wide application of NLP models in crucial are...
Collecting dialogue state labels, slots and values, for learning dialogu...
Deep-learning-based NLP models are found to be vulnerable to word
substi...
This paper introduces the system submitted by the Yidun NISP team to the...
This paper introduces a notation of ε-weakened robustness for
analyzing ...
Geohazards such as landslides have caused great losses to the safety of
...
Deep networks for image processing typically learn from RGB pixels. This...
Utility mining has emerged as an important and interesting topic owing t...
Rapid development of Internet technologies promotes traditional newspape...
This paper introduces a general method to approximate the convolution of...