Speech_Enhancement_with_UNET:塞萨洛尼基亚里斯多德大学-电气和计算机工程-音频和视频技术-课程分配

上传者: 42157166 | 上传时间: 2022-05-17 04:41:59 | 文件大小: 139.29MB | 文件类型: ZIP
使用UNET增强语音 塞萨洛尼基亚里斯多德大学-电气和计算机工程 课程:音频和视频技术 作者: , , , 该存储库包含音频和视频技术课程的作业。 目的是要了解深度学习的分支并将其应用于人类语音的去噪问题。 数据集 使用的数据集是 (Microsoft可缩放的嘈杂语音数据库)。 借助其提供的功能,并在选择了特定类型的噪声之后,将它们与各种SNR比率(0 dB,5 dB,10 dB,15 dB,20 dB)的清晰语音信号混合,从而总共得到4种噪声。小时的训练集和30分钟的测试集已创建。 可以在s01_CreateWAVs.py文件中找到此过程。 在Dataset_MS_SNSD和Dataset_My_Wavs文件夹中,有一些屏幕截图,显示了如何将音频文件放置在原始和最终集中。 网络 可以在s03_InitializeModel.py文件中找到使用的模型,并可以在下图中看到它: 请注意

文件下载

资源详情

[{"title":"( 67 个子文件 139.29MB ) Speech_Enhancement_with_UNET:塞萨洛尼基亚里斯多德大学-电气和计算机工程-音频和视频技术-课程分配","children":[{"title":"Speech_Enhancement_with_UNET-master","children":[{"title":"s00_tools.py <span style='color:#111;'> 1.26KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 3.13KB </span>","children":null,"spread":false},{"title":"s07_AudioExamples","children":[{"title":"NoisySpeech02.wav <span style='color:#111;'> 625.06KB </span>","children":null,"spread":false},{"title":"CleanSpeech01.wav <span style='color:#111;'> 625.06KB </span>","children":null,"spread":false},{"title":"CleanSpeech02.wav <span style='color:#111;'> 625.06KB </span>","children":null,"spread":false},{"title":"NoisySpeech01_Figures","children":[{"title":"Waveform_Noisy_Speech.png <span style='color:#111;'> 18.16KB </span>","children":null,"spread":false},{"title":"Waveform_Enhanced_Speech.png <span style='color:#111;'> 18.74KB </span>","children":null,"spread":false},{"title":"Magnitude_Spectogram_Enhanced_Speech.png <span style='color:#111;'> 30.66KB </span>","children":null,"spread":false},{"title":"Magnitude_Spectogram_Noisy_Speech.png <span style='color:#111;'> 40.92KB </span>","children":null,"spread":false}],"spread":true},{"title":"NoisySpeech01.wav <span style='color:#111;'> 625.06KB </span>","children":null,"spread":false}],"spread":true},{"title":"s02_CreateSpects.py <span style='color:#111;'> 6.27KB </span>","children":null,"spread":false},{"title":"Dataset_My_Wavs","children":[{"title":"Screenshot_1.png <span style='color:#111;'> 5.33KB </span>","children":null,"spread":false},{"title":"Screenshot_2.png <span style='color:#111;'> 8.52KB </span>","children":null,"spread":false}],"spread":true},{"title":"s06_CreateEnhancedAudioAndEvaluate.py <span style='color:#111;'> 8.76KB </span>","children":null,"spread":false},{"title":"s07_UseUNetExample.py <span style='color:#111;'> 5.54KB </span>","children":null,"spread":false},{"title":"s04_TrainModel.py <span style='color:#111;'> 3.34KB </span>","children":null,"spread":false},{"title":"UNET_Model_Saves","children":[{"title":"UNET_Shape.png <span style='color:#111;'> 65.64KB </span>","children":null,"spread":false},{"title":"Saved_Model","children":[{"title":"variables","children":[{"title":"variables.index <span style='color:#111;'> 10.52KB </span>","children":null,"spread":false},{"title":"variables.data-00000-of-00001 <span style='color:#111;'> 22.25MB </span>","children":null,"spread":false}],"spread":true},{"title":"saved_model.pb <span style='color:#111;'> 802.35KB </span>","children":null,"spread":false}],"spread":true},{"title":"UNET_Model_Weights.h5 <span style='color:#111;'> 7.51MB </span>","children":null,"spread":false},{"title":"UNET_Model.json <span style='color:#111;'> 23.22KB </span>","children":null,"spread":false}],"spread":true},{"title":"s05_CreateEnhancedSpectsForTest.py <span style='color:#111;'> 2.52KB </span>","children":null,"spread":false},{"title":"s01_CreateWAVs.py <span style='color:#111;'> 12.24KB </span>","children":null,"spread":false},{"title":"__results","children":[{"title":"clean_huber_normX","children":[{"title":"Figure 2021-02-21 201551.png <span style='color:#111;'> 16.48KB </span>","children":null,"spread":false},{"title":"UNET_Model_Saves","children":[{"title":"Saved_Model","children":[{"title":"variables","children":[{"title":"variables.index <span style='color:#111;'> 10.52KB </span>","children":null,"spread":false},{"title":"variables.data-00000-of-00001 <span style='color:#111;'> 22.25MB </span>","children":null,"spread":false}],"spread":false},{"title":"saved_model.pb <span style='color:#111;'> 802.42KB </span>","children":null,"spread":false}],"spread":false},{"title":"UNET_Model_Weights.h5 <span style='color:#111;'> 7.51MB </span>","children":null,"spread":false},{"title":"UNET_Model.json <span style='color:#111;'> 23.22KB </span>","children":null,"spread":false}],"spread":false},{"title":"eval.txt <span style='color:#111;'> 2.90KB </span>","children":null,"spread":false}],"spread":true},{"title":"_graphs","children":[{"title":"pred02.png <span style='color:#111;'> 24.24KB </span>","children":null,"spread":false},{"title":"loss03.png <span style='color:#111;'> 26.26KB </span>","children":null,"spread":false},{"title":"norm01.png <span style='color:#111;'> 48.66KB </span>","children":null,"spread":false},{"title":"pred01.png <span style='color:#111;'> 25.71KB </span>","children":null,"spread":false},{"title":"norm03.png <span style='color:#111;'> 26.27KB </span>","children":null,"spread":false},{"title":"loss02.png <span style='color:#111;'> 24.99KB </span>","children":null,"spread":false},{"title":"norm02.png <span style='color:#111;'> 24.92KB </span>","children":null,"spread":false},{"title":"loss01.png <span style='color:#111;'> 25.40KB </span>","children":null,"spread":false},{"title":"pred03.png <span style='color:#111;'> 26.05KB </span>","children":null,"spread":false}],"spread":false},{"title":"clean_mse_normX","children":[{"title":"UNET_Model_Saves","children":[{"title":"Saved_Model","children":[{"title":"variables","children":[{"title":"variables.index <span style='color:#111;'> 10.52KB </span>","children":null,"spread":false},{"title":"variables.data-00000-of-00001 <span style='color:#111;'> 22.25MB </span>","children":null,"spread":false}],"spread":false},{"title":"saved_model.pb <span style='color:#111;'> 802.35KB </span>","children":null,"spread":false}],"spread":false},{"title":"UNET_Model_Weights.h5 <span style='color:#111;'> 7.51MB </span>","children":null,"spread":false},{"title":"UNET_Model.json <span style='color:#111;'> 23.22KB </span>","children":null,"spread":false}],"spread":false},{"title":"eval.txt <span style='color:#111;'> 2.90KB </span>","children":null,"spread":false},{"title":"03_Figure 2021-02-16 142646.png <span style='color:#111;'> 17.50KB </span>","children":null,"spread":false}],"spread":false},{"title":"_graphs.xlsx <span style='color:#111;'> 54.87KB </span>","children":null,"spread":false},{"title":"noise_mse_normX","children":[{"title":"UNET_Model_Saves","children":[{"title":"Saved_Model","children":[{"title":"variables","children":[{"title":"variables.index <span style='color:#111;'> 10.52KB </span>","children":null,"spread":false},{"title":"variables.data-00000-of-00001 <span style='color:#111;'> 22.25MB </span>","children":null,"spread":false}],"spread":false},{"title":"saved_model.pb <span style='color:#111;'> 799.11KB </span>","children":null,"spread":false}],"spread":false},{"title":"UNET_Model_Weights.h5 <span style='color:#111;'> 7.51MB </span>","children":null,"spread":false},{"title":"UNET_Model.json <span style='color:#111;'> 23.13KB </span>","children":null,"spread":false}],"spread":false},{"title":"Figure 2021-02-21 193712.png <span style='color:#111;'> 18.45KB </span>","children":null,"spread":false},{"title":"eval.txt <span style='color:#111;'> 2.90KB </span>","children":null,"spread":false}],"spread":false},{"title":"clean_mse_normY","children":[{"title":"UNET_Model_Saves","children":[{"title":"Saved_Model","children":[{"title":"variables","children":[{"title":"variables.index <span style='color:#111;'> 10.52KB </span>","children":null,"spread":false},{"title":"variables.data-00000-of-00001 <span style='color:#111;'> 22.25MB </span>","children":null,"spread":false}],"spread":false},{"title":"saved_model.pb <span style='color:#111;'> 799.11KB </span>","children":null,"spread":false}],"spread":false},{"title":"UNET_Model_Weights.h5 <span style='color:#111;'> 7.51MB </span>","children":null,"spread":false},{"title":"UNET_Model.json <span style='color:#111;'> 23.13KB </span>","children":null,"spread":false}],"spread":false},{"title":"Figure 2021-02-21 184220.png <span style='color:#111;'> 16.00KB </span>","children":null,"spread":false},{"title":"eval.txt <span style='color:#111;'> 2.90KB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"s03_InitializeModel.py <span style='color:#111;'> 5.49KB </span>","children":null,"spread":false},{"title":"Dataset_MS_SNSD","children":[{"title":"Screenshot_1.png <span style='color:#111;'> 4.02KB </span>","children":null,"spread":false},{"title":"Screenshot_2.png <span style='color:#111;'> 5.90KB </span>","children":null,"spread":false}],"spread":false},{"title":"Dataset_My_Spects","children":[{"title":"Screenshot_1.png <span style='color:#111;'> 8.06KB </span>","children":null,"spread":false}],"spread":false},{"title":"report.pdf <span style='color:#111;'> 1.25MB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明