Blog(2)

• TFPSNet Time-Frequency Domain Path Scanning Network for Speech Separation

  Deep learning techniques have accomplished a big step forward on speech separation task. The current leading methods are based on the time-domain audio separation network (TasNet) [1]. TasNet uses a learnable encoder and decoder to replace the fixed T-F domain transformation. It takes waveform inputs and directly reconstructs sources, and computes time-domain loss with utterance-level permutation invariant training (uPIT). Several approaches are proposed based on TasNet framework, such as the Conv-TasNet [2] , the dual-path recurrent neural network (DPRNN) [3], the dual-path Transformer network (DPTNet) [4], RNN-free transformer-based neural network (SepFormer) [5] , a self-attentive network with a novel sandglass-shape, namely Sandglasset [6].

• FedMargin - Federated Learning via Attentive Margin of Semantic Feature Representations

  Let’s play a simple game. Open the photo gallery on your phone and briefly scroll your images, do you see some patterns and recognize the objects you like on the images?

Research Areas(0)

Publications(352)

• Tail Call Optimization Tailored for Native Stack Utilization in JavaScript Runtimes

  AuthorHyukwoo Park, Seonghyun Kim

  PublishedIEEE Access

  Date2024-08-12

• EDgE: Enhancing Predictability in Decentralized Network Slices through Federated Learning – A Multi layered Ecosystem

  AuthorGanesh Chandrasekaran; Abhinay Kumar; Karthikeyan Subramaniam; N Sunil; Rajesh Challa

  PublishedIEEE Access

  Date2024-07-17

• Contamination by Idle RIS in Cellular Systems - Impacts and Solutions

  AuthorMohammed Saquib Noorulhuda Khan, Ashok Kumar Reddy Chavva

  PublishedIEEE Wireless Communications and Networking Conference (WCNC)

  Date2024-07-03

View More

News(38)

• Samsung's New Breakthrough in Speech and Image Signal Processing

  The 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) has accepted five research papers from Samsung R&D Institute China-Beijing (SRC-B). ICASSP, organized by the Institute of Electrical and Electronics Engineers (IEEE), represents a premier international conference in signal processing with substantial international influence.

• Samsung Researchers Receive Prestigious Best Paper Award at IEEE ICC 2024

  Samsung R&D Institute India-Bangalore (SRI-B) is proud to announce that its Network R&D team has received the Best Research Paper Award at the esteemed IEEE International Conference on Communications (ICC) 2024 workshop (BlockSecSDN 2024), held on June 13th, 2024 in Denver, Colorado, USA.

• Samsung Research Fellow Juho Lee Named Inaugural Recipient of IEEE ComSoc Excellence in Supporting Standardization for Communications Award

  Juho Lee, a fellow at Samsung Electronics’ advanced R&D hub Samsung Research (SR), received a Career Award for his outstanding leadership and technical contributions in standardization of wireless communication from the Institute of Electrical and Electronics Engineers (IEEE) — the world’s largest technical professional organization dedicated to advancing technology for the benefit of humanity.

View More

Others(0)