Coder Social home page Coder Social logo

模型输入不统一? about ecapa-tdnn HOT 7 CLOSED

taoruijie avatar taoruijie commented on August 19, 2024
模型输入不统一?

from ecapa-tdnn.

Comments (7)

TaoRuijie avatar TaoRuijie commented on August 19, 2024

请check这里 #34 (comment) mse的内容可以参考对应文章

Beijing ZKJ-NPU Speaker Verification System for VoxCeleb Speaker Recognition Challenge 2021

from ecapa-tdnn.

JJun-Guo avatar JJun-Guo commented on August 19, 2024

请check这里 #34 (comment) mse的内容可以参考对应文章

Beijing ZKJ-NPU Speaker Verification System for VoxCeleb Speaker Recognition Challenge 2021

好的,感谢您的回复!如果我对模型进行fine-tune一个新的speaker的话,n_class这个参数是不是设为1就可以了?

from ecapa-tdnn.

TaoRuijie avatar TaoRuijie commented on August 19, 2024

理论上我并不觉得这么finetune是合理的

即使要要这么做,也要在dataloader里把新的speaker赋予大于原speaker数目的类别标签,如5995.

from ecapa-tdnn.

JJun-Guo avatar JJun-Guo commented on August 19, 2024

理论上我并不觉得这么finetune是合理的

即使要要这么做,也要在dataloader里把新的speaker赋予大于原speaker数目的类别标签,如5995.

您觉得不合理是指speaker的数量太少会使模型坍塌到该speaker吗?还是说finetune的数据量(speaker下的语音数据)不能过小?

from ecapa-tdnn.

TaoRuijie avatar TaoRuijie commented on August 19, 2024

我没有读过用多一类来finetune的做法 所以我不能确定会有好的结果

from ecapa-tdnn.

JJun-Guo avatar JJun-Guo commented on August 19, 2024

我没有读过用多一类来finetune的做法 所以我不能确定会有好的结果

明白!您尝试过将vad应用到声纹识别场景吗?理论上是需要vad去除一些干扰音再进行比对?

from ecapa-tdnn.

TaoRuijie avatar TaoRuijie commented on August 19, 2024

voxceleb2不需要这一步,请阅读一些比赛的相关的报告

from ecapa-tdnn.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.