Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

An Empirical Study of Language Model Integration for Transducer based Speech Recognition



Huahuan Zheng , Keyu An , Zhijian Ou , Chen Huang , Ke Ding , Guanglu Wan

* submitted to INTERSPEECH 2022 

   Access Paper or Ask Questions

CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR



Keyu An , Huahuan Zheng , Zhijian Ou , Hongyu Xiang , Ke Ding , Guanglu Wan

* submitted to INTERSPEECH 2022 

   Access Paper or Ask Questions

Exploiting Single-Channel Speech for Multi-Channel End-to-End Speech Recognition: A Comparative Study



Keyu An , Zhijian Ou

* submitted to INTERSPEECH 2022. arXiv admin note: substantial text overlap with arXiv:2107.02670 

   Access Paper or Ask Questions

Multilingual and crosslingual speech recognition using phonological-vector based phone embeddings



Chengrui Zhu , Keyu An , Huahuan Zheng , Zhijian Ou


   Access Paper or Ask Questions

Exploiting Single-Channel Speech For Multi-channel End-to-end Speech Recognition



Keyu An , Zhijian Ou

* submitted to ASRU 2021 

   Access Paper or Ask Questions

Deformable TDNN with adaptive receptive fields for speech recognition



Keyu An , Yi Zhang , Zhijian Ou

* 5 pages. submitted to Interspeech 2021 

   Access Paper or Ask Questions

Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients



Huahuan Zheng , Keyu An , Zhijian Ou

* Accepted by IEEE SLT 2021 

   Access Paper or Ask Questions

CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency



Keyu An , Hongyu Xiang , Zhijian Ou

* 5 pages. arXiv admin note: text overlap with arXiv:1911.08747 

   Access Paper or Ask Questions

CAT: CRF-based ASR Toolkit



Keyu An , Hongyu Xiang , Zhijian Ou

* Code released at: https://github.com/thu-spmi/cat 

   Access Paper or Ask Questions