Yuke Li

Orcid: 0009-0003-0935-2483

Affiliations:
  • NetEase Yidun AI Lab, Hangzhou, China


According to our database1, Yuke Li authored at least 18 papers between 2021 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of five.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
SELECT: Detecting Label Errors in Real-world Scene Text Data.
Proceedings of the 7th ACM International Conference on Multimedia in Asia, 2025

Bridging the Modality Gap for Speech-image Retrieval with Text Supervision.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASR.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024
Enhancing Unified Streaming and Non-Streaming ASR Through Curriculum Learning With Easy-To-Hard Tasks.
Proceedings of the IEEE Spoken Language Technology Workshop, 2024

Cross-Modal Denoising: A Novel Training Paradigm for Enhancing Speech-Image Retrieval.
Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Learning from Back Chunks: Acquiring More Future Knowledge for Streaming ASR Models via Self Distillation.
Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Coarse-to-fine Alignment Makes Better Speech-image Retrieval.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2024

DeCMG: Denoise with Cross-modality Guidance Makes Better Text-Video Retrieval.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2024

HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition.
Proceedings of the IEEE International Conference on Acoustics, 2024

Differentiable Resolution Compression and Alignment for Efficient Video Classification and Retrieval.
Proceedings of the IEEE International Conference on Acoustics, 2024

2023
Enhancing the Unified Streaming and Non-streaming Model with Contrastive Learning.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

3D-CSL: Self-Supervised 3D Context Similarity Learning for Near-Duplicate Video Retrieval.
Proceedings of the IEEE International Conference on Image Processing, 2023

Improving CTC-Based ASR Models With Gated Interlayer Collaboration.
Proceedings of the IEEE International Conference on Acoustics, 2023

LAE-ST-MOE: Boosted Language-Aware Encoder Using Speech Translation Auxiliary Task for E2E Code-Switching ASR.
Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022
Acoustic Pornography Recognition Using Convolutional Neural Networks and Bag of Refinements.
CoRR, 2022

Multi-Level Modeling Units for End-to-End Mandarin Speech Recognition.
Proceedings of the 13th International Symposium on Chinese Spoken Language Processing, 2022

2021
BBS-KWS: The Mandarin Keyword Spotting System Won the Video Keyword Wakeup Challenge.
CoRR, 2021


  Loading...