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?

Focus Areas(0)

Research Achievements(263)

• Self-Supervised Transformer Architecture for Change Detection in Radio Access Networks

  AuthorIgor Kozlov, Dmitriy Rivkin, Wei-Di Chang, Di Wu, Xue Liu, Gregory Dudek

  PublishedIEEE International Conference on Communications (ICC)

  Date2023-05-28

• Multi-agent Attention Actor-Critic Algorithm for Load Balancing in Cellular Networks

  AuthorJikun Kang, Di Wu, Ju Wang, Ekram Hossain, Xue Liu, Gregory Dudek.

  PublishedIEEE International Conference on Communications (ICC)

  Date2023-05-28

• Mixed-Variable PSO with Fairness on Multi-Objective Field Data Replication in Wireless Networks

  AuthorDun Yuan, Yujin Nam, Amal Feriani, Abhisek Konar, Di Wu, Seowoo Jang, Xue Liu, Gregor

  PublishedIEEE International Conference on Communications (ICC)

  Date2023-05-28

View More

News(34)

• SRC-B's New Achievement in the Field of 5G

  Samsung R&D Institute China-Beijing (SRC-B) published three papers recently accepted by the 97th Institute of Electrical and Electronics Engineers (IEEE) Vehicular Technology Conference: VTC2023-Spring, to be held in Florence from June 20 to 23, 2023.

• SRC-B’s New Achievement in the Field of 5G

  Samsung R&D Institute China-Beijing (SRC-B) published three papers recently accepted by the 97th Institute of Electrical and Electronics Engineers (IEEE) Vehicular Technology Conference: VTC2023-Spring, to be held in Florence from June 20 to 23, 2023.

• Samsung R&D Institute Poland Placed 2^nd in DCASE 2023 Challenge

  Samsung R&D Institute Poland (SRPOL) garnered recognition as a prominent participant in the Detection and Classification of Acoustic Scenes and Events (DCASE) 2023 challenge, organized by the Institute of Electrical and Electronics Engineers (IEEE).

View More

Others(0)