LRS3-For-Speech-Separation:LRS3数据集上的多模式语音分离任务数据生成脚本

上传者: 42127775 | 上传时间: 2026-02-03 22:03:46 | 文件大小: 3.48MB | 文件类型: ZIP
生成数据的指令 以下是生成训练和测试数据的步骤。 有几个参数可以更改以匹配不同的目的。 我们将尽快在LRS3数据集上发布语音分离基准。 我们的脚本存储库是为了使多模式语音分离任务在数据集生成方面具有统一的标准。 这样我们就可以跟进多模式语音分离任务。 我们希望LRS3数据集将为诸如WSJ0数据集之类的纯语音分离任务制定统一的生成标准。 :check_box_with_check: 我们的基准模型即将推出! 信噪比 信噪比 基准线 15.08 15.34 要求 ffmpeg 4.2.1 袜14.4.2 numpy的1.17.2 OpenCVPython的4.1.2.30 librosa 0.7.0 dlib 19.19.0 face_recognition 1.3.0 第1步-获取原始数据 在这种方法中,我们使用“数据集作为我们的训练,验证和测试集。 Afouras T,Chung JS,Senior

文件下载

资源详情

[{"title":"( 27 个子文件 3.48MB ) LRS3-For-Speech-Separation:LRS3数据集上的多模式语音分离任务数据生成脚本","children":[{"title":"LRS3-For-Speech-Separation-master","children":[{"title":"video_process","children":[{"title":".ipynb_checkpoints","children":[{"title":"check_mouth-checkpoint.py <span style='color:#111;'> 434B </span>","children":null,"spread":false},{"title":"video-checkpoint.log <span style='color:#111;'> 30B </span>","children":null,"spread":false},{"title":"video_to_np-checkpoint.py <span style='color:#111;'> 2.97KB </span>","children":null,"spread":false},{"title":"video_path-checkpoint.txt <span style='color:#111;'> 1.23MB </span>","children":null,"spread":false},{"title":"video_process-checkpoint.py <span style='color:#111;'> 6.28KB </span>","children":null,"spread":false}],"spread":true},{"title":"video_to_np.py <span style='color:#111;'> 2.75KB </span>","children":null,"spread":false},{"title":"video_process.py <span style='color:#111;'> 6.34KB </span>","children":null,"spread":false},{"title":"valid_mouth.txt <span style='color:#111;'> 400.83KB </span>","children":null,"spread":false},{"title":"video_path.txt <span style='color:#111;'> 1010.04KB </span>","children":null,"spread":false}],"spread":true},{"title":".DS_Store <span style='color:#111;'> 8.00KB </span>","children":null,"spread":false},{"title":"test.txt <span style='color:#111;'> 5.27KB </span>","children":null,"spread":false},{"title":"train.txt <span style='color:#111;'> 351.56KB </span>","children":null,"spread":false},{"title":"val.txt <span style='color:#111;'> 26.37KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 3.36KB </span>","children":null,"spread":false},{"title":"audio_process","children":[{"title":".ipynb_checkpoints","children":[{"title":"mix_2_spk_tr-checkpoint.txt <span style='color:#111;'> 8.52MB </span>","children":null,"spread":false},{"title":"audio_mix-checkpoint.py <span style='color:#111;'> 2.73KB </span>","children":null,"spread":false}],"spread":true},{"title":"maxfilt.m <span style='color:#111;'> 4.70KB </span>","children":null,"spread":false},{"title":"audio_cut.py <span style='color:#111;'> 2.63KB </span>","children":null,"spread":false},{"title":"mix_2_spk_tt.txt <span style='color:#111;'> 471.05KB </span>","children":null,"spread":false},{"title":"check_file.py <span style='color:#111;'> 328B </span>","children":null,"spread":false},{"title":"mix_2_spk_tr.txt <span style='color:#111;'> 7.76MB </span>","children":null,"spread":false},{"title":"audio_path.py <span style='color:#111;'> 5.01KB </span>","children":null,"spread":false},{"title":"activlev.m <span style='color:#111;'> 16.29KB </span>","children":null,"spread":false},{"title":"mix_2_spk_cv.txt <span style='color:#111;'> 775.28KB </span>","children":null,"spread":false},{"title":"create_wav_2speakers.m <span style='color:#111;'> 8.95KB </span>","children":null,"spread":false},{"title":"audio_check.py <span style='color:#111;'> 328B </span>","children":null,"spread":false}],"spread":false},{"title":".gitignore <span style='color:#111;'> 49B </span>","children":null,"spread":false}],"spread":true}],"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