Recent News

  • [March. 19, 2019] Our DKU system was ranked in 3rd place on VOiCES Challenge.
  • [March. 16, 2019] Our primary system submitted to ASVSpoof 2019 physical access task was ranked at 4th among the world.
  • [Feb. 10, 2019] My paper submitted to ICASSP 2019 was accepted as a poster presentation.
  • [Nov. 18, 2018] The DKU-Tencent system jointly built by our lab and Tencent Inc. for the Oriental Language Recognition (OLR) 2018 short utterance task was ranked at 2nd place.
  • [Nov. 01, 2018] Our DKU-SMIIP system was ranked at 4th place among worlds’s most competitive research community for the NIST SRE 2018.
  • [Aug. 10, 2018] My co-authored paper submitted to ISCSLP 2018 was accepted.
  • [Jun. 06, 2018] One of my submitted paper to Interspeech 2018 was accepted, I will come to India on Sep. 2-6.
  • [Mar. 30, 2018] My first-author paper has been accepted by Speaker Odyssey 2018. This is a great honor for me as a speaker and language recognition researcher.
  • [Jan. 30, 2018] I’m very happy to share that my two first-author paper got accepted by ICASSP 2018, the top international conference in the area of audio and speech processing.

Selected Publications

. Utterance-level end-to-end language identification using attention-based CNN-BLSTM. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019.

Preprint

. End-to-end Language Identification using NetFV and NetVLAD. International Symposium on Chinese Spoken Language Processing (ISCSLP), 2018.

Preprint Poster

. Analysis of Length Normalization in End-to-End Speaker Verification System. INTERSPEECH, 2018.

Preprint PDF Poster

. Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System . The Speaker and Language Recognition Workshop (Speaker Odyssey), 2018.

Preprint PDF

. A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018.

Preprint Poster

. Insights into End-to-End Learning Scheme for Language Identification. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018.

Preprint Poster

. Countermeasures for Automatic Speaker Verification Replay Spoofing Attack : On Data Augmentation, Feature Representation, Classification and Fusion. INTERSPEECH, 2017.

PDF

Contact

  • caiwch3@mail2.sysu.edu.cn
  • 132 East Waihuan Road, Guangzhou Higher Education Mega Center (University Town), Guangzhou 510006, P. R. China