EDN

Self-correcting codes conquer noise, part one: Viterbi codecs

FEC (forward-error-correction) techniques correct errors at the receiver end of digital communications systems. In contrast with error-detection and retransmission ...
IEEE

Video Captioning Using Inflated 3D Convolution Network Encoder with Decoder for Video Content

Abstract: Video captioning is a process of automatically generating textual descriptions for video content. This task is crucial in the fields of computer vision and Natural Language Processing (NLP).
GitHub

DisCoder: High-Fidelity Music Vocoder Using Neural Audio Codecs

DisCoder is a neural vocoder that leverages a generative adversarial encoder-decoder architecture informed by a neural audio codec to reconstruct high-fidelity 44.1 kHz audio from mel spectrograms.
GitHub

OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model

We present OpenS2S, a fully open-source, transparent and end-to-end large speech language model designed to enable empathetic speech interactions. As shown in the figure, OpenS2S consists of the ...
IEEE

Multi-Scale Moving Object Detection in Complex Video Using a Modified Encoder-Decoder Framework

Abstract: Computer vision frequently applies background subtraction (BGS) as a core technique, particularly in fields such as surveillance, object detection, and motion analysis. The main goal of BGS ...