Search Results for author: Borching Su

Found 5 papers, 0 papers with code

MIMO Speech Compression and Enhancement Based on Convolutional Denoising Autoencoder

no code implementations24 May 2020 You-Jin Li, Syu-Siang Wang, Yu Tsao, Borching Su

For speech-related applications in IoT environments, identifying effective methods to handle interference noises and compress the amount of data in transmissions is essential to achieve high-quality services.

Denoising

Speech Enhancement Based on Cyclegan with Noise-informed Training

no code implementations19 Oct 2021 Wen-Yuan Ting, Syu-Siang Wang, Hsin-Li Chang, Borching Su, Yu Tsao

Herein, we investigate a potential limitation of the clean-to-noisy conversion part and propose a novel noise-informed training (NIT) approach to improve the performance of the original CycleGAN SE system.

Speech Enhancement

Waveform Design for Optimal PSL Under Spectral and Unimodular Constraints via Alternating Minimization

no code implementations16 Oct 2022 Chin-wei Huang, Li-Fu Chen, Borching Su

It is observed in the numerical results that the PSL of the proposed algorithm is close to the derived lower bound.

IANS: Intelligibility-aware Null-steering Beamforming for Dual-Microphone Arrays

no code implementations9 Jul 2023 Wen-Yuan Ting, Syu-Siang Wang, Yu Tsao, Borching Su

Beamforming techniques are popular in speech-related applications due to their effective spatial filtering capabilities.

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