Search Results for author: Xiguang Zheng

Found 5 papers, 2 papers with code

RAMP: Retrieval-Augmented MOS Prediction via Confidence-based Dynamic Weighting

no code implementations31 Aug 2023 Hui Wang, Shiwan Zhao, Xiguang Zheng, Yong Qin

Automatic Mean Opinion Score (MOS) prediction is crucial to evaluate the perceptual quality of the synthetic speech.

Retrieval Self-Supervised Learning

Multi-scale temporal-frequency attention for music source separation

no code implementations2 Sep 2022 LianWu Chen, Xiguang Zheng, Chen Zhang, Liang Guo, Bing Yu

In recent years, deep neural networks (DNNs) based approaches have achieved the start-of-the-art performance for music source separation (MSS).

Music Source Separation

L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment

1 code implementation21 Feb 2022 Eric Guizzo, Christian Marinoni, Marco Pennese, Xinlei Ren, Xiguang Zheng, Chen Zhang, Bruno Masiero, Aurelio Uncini, Danilo Comminiello

The L3DAS22 Challenge is aimed at encouraging the development of machine learning strategies for 3D speech enhancement and 3D sound localization and detection in office-like environments.

Sound Event Localization and Detection Speech Enhancement

Cannot find the paper you are looking for? You can Submit a new open access paper.