Abstract: This paper proposes StreamCodec, a streamable neural audio codec designed for real-time communication. StreamCodec adopts a fully causal, symmetric encoder-decoder structure and operates in ...
Abstract: This letter presents a finite-rate deep-learning (DL)-based channel state information (CSI) feedback method for massive multiple-input multiple-output (MIMO) systems. The presented method ...
This Repository is an official implementation of "CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization". The paper has been accepted at ECCV 2024. Compact3D is a method to reduce the ...
This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. SpeechTokenizer is a unified speech tokenizer for speech language models ...