Improving Generalization Over Unseen Noise for Speech Enhancement with Ensemble of Multi-branched Regressions
碩士 === 國立臺灣大學 === 電子工程學研究所 === 107 === Speech enhancement (SE) algorithm aims to prune undesired contents within a noise contaminated speech. Recent years, deep learning based SE algorithms acquired huge improvements in denoising performances. Despite its great improvements from past SE algorithms,...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2019
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/zv2v2t |