Enhanced Neural Beamformer with Spatial Information for Target Speech Extraction

no code implementations • 28 Jun 2023 • Aoqi Guo, Junnan Wu, Peng Gao, Wenbo Zhu, Qinwen Guo, Dazhi Gao, Yujun Wang

In this paper, we propose a target speech extraction network that utilizes spatial information to enhance the performance of neural beamformer.

Dimensionality Reduction Speech Extraction

Dynamic Interactional And Cooperative Network For Shield Machine

no code implementations • 17 Nov 2022 • Dazhi Gao, Rongyang Li, Hongbo Wang, Lingfeng Mao, Huansheng Ning

Then, according to the relationship, models were established for the control terminal, including SM rate prediction and SM anomaly detection.

Anomaly Detection

Training a U-Net based on a random mode-coupling matrix model to recover acoustic interference striations

no code implementations • 24 Mar 2020 • Xiaolei Li, Wenhua Song, Dazhi Gao, Wei Gao, Haozhong Wan

A U-Net is trained to recover acoustic interference striations (AISs) from distorted ones.

Sound source ranging using a feed-forward neural network with fitting-based early stopping

no code implementations • 1 Apr 2019 • Jing Chi, Xiaolei Li, Haozhong Wang, Dazhi Gao, Peter Gerstoft

Based on FEAST, when the evaluated range error of the FNN reaches the minimum on test data, stopping training, which will help to improve the ranging accuracy of the FNN on the test data.