《Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verifi》
摘要：在嘈雜環境中提高語音系統性能仍然是一項具有挑戰性的任務，語音增強（SE）是解決該問題的有效技術之一。由於生成對抗網絡（GAN）在各種圖像處理任務中的有發展前景的實驗結果，我們探索條件GAN（cGAN）對SE的潛力，特別是，我們利用Isola提出的圖像處理框架[1] ]學習從嘈雜語音的譜圖到增強對應物的映射。SEcGAN由兩個以對抗方式訓練的網絡組成：一個試圖增強輸入噪聲頻譜圖的生成器，以及一
相關文章
- 1. Segan : Speech Enhancement Generative Adversarial Network
- 2. Speech Enhancement Generation Adversarial Network
- 3. Conditional Generative Adversarial Networks（CGAN）筆記
- 4. FACE AGING WITH CONDITIONAL GENERATIVE ADVERSARIAL NETWORKS
- 5. Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow
- 6. Conditional Generative Adversarial Nets
- 7. CartoonGAN: Generative Adversarial Networks for Photo Cartoonization
- 8. Generative Adversarial Networks for Hyperspectral Image Classification
- 9. Graphical Generative Adversarial Networks
- 10. Conditional Generative Adversarial Nets（CGAN）
- 更多相關文章...
- • Swift for 循環 - Swift 教程
- • Scala for循環 - Scala教程
- • RxJava操作符（七）Conditional and Boolean
- • 算法總結-股票買賣
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Segan : Speech Enhancement Generative Adversarial Network
- 2. Speech Enhancement Generation Adversarial Network
- 3. Conditional Generative Adversarial Networks（CGAN）筆記
- 4. FACE AGING WITH CONDITIONAL GENERATIVE ADVERSARIAL NETWORKS
- 5. Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow
- 6. Conditional Generative Adversarial Nets
- 7. CartoonGAN: Generative Adversarial Networks for Photo Cartoonization
- 8. Generative Adversarial Networks for Hyperspectral Image Classification
- 9. Graphical Generative Adversarial Networks
- 10. Conditional Generative Adversarial Nets（CGAN）