Blog(4)

• Better Exploiting Spatial Separability in Multichannel Speech Enhancement with an Align-and-Filter Network

  Voice has played a vital role in our daily communications with family, friends and colleagues, as well as in interactions with our intelligent devices.

• FSPEN: An Ultra-Lightweight Network for Real Time Speech Enhancement

  Speech enhancement or noise suppression aims at improving the quality and intelligibility of noisy speech. It is an important frontend module for voice call, automatic speech recognition (ASR), and hearing aids system.

• A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation

  I have a challenge: I am going to show you a very noisy image. Would you be able to recognize its content confidently? No? Neither can AI models. Like humans, they find it challenging to understand the content of corrupted images and, sadly, they tend to be much more sensitive to the problem than we are.

View More

Research Areas(0)

Publications(41)

• On the Importance of a Multi-Scale Calibration for Quantization

  AuthorIngyu Seong, Hyemi Jang, Yongkweon Jeon

  PublishedIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

  Date2026-05-04

• DRLCQ: Deep Reinforcement Learning based Call Quality Enhancement in O-RAN

  AuthorSukhdeep Singh, Swaraj Kumar, Ashish Jain, Madhan Raj Kanagarathinam, Neelmani Jha, Moonki Hong

  PublishedIEEE Global Communications Conference

  Date2026-03-19

• Better Exploiting Spatial Separability in Multichannel Speech Enhancement with an Align-and-Filter Framework

  AuthorChinghua Lee, Chouchang Yang, Yashas Malur Saidutta, Retiree, Yilin Shen, Hongxia Jin

  PublishedInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP)

  Date2024-12-21

View More

News(17)

• [Blog] Unified CSI Reconstruction and Prediction with Channel Attention Mechanism

  The study of Artificial Intelligence (AI)-based Channel State Information (CSI) feedback enhancement has shown great potential in reducing feedback overhead, and overcoming channel aging issues in massive multiple-input multiple-output systems.

• Celebrating Samsung R&D Institute China-Beijing's Outstanding Achievements at NTIRE at the CVPR 2026

  The New Trends in Image Restoration and Enhancement (NTIRE 2026) workshop, held alongside the Conference on Computer Vision and Pattern Recognition (CVPR 2026), served as a key venue for sharing the latest advances in image processing and restoration.

• [Blog] A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions

  Introduce a lightweight hybrid dual-channel speech enhancement system that combines IVA with a modified dual-channel GTCRN to achieve effective speech enhancement in low-SNR conditions.

View More

Others(0)