Comments (7)
qiuqiangkong
commented on August 27, 2024
您好！您看到的代码是论文之后复现的，我们发现绝对值比平方PESQ有0.1左右的提升。所以在代码中使用了绝对值loss。
Best wishes,
Qiuqiang
…________________________________
From: JohnChen1124 <[email protected]>
Sent: 23 June 2018 11:07:35
To: yongxuUSTC/sednn
Cc: Subscribed
Subject: [yongxuUSTC/sednn] 模型�入特徵��}�教 (#13)
您好:
非常感x你��所完成的程式，希望能抽空回答一��小小的��}。模型�入特徵取完lV大小之後有做^�χ担孟�]有取平方，但在A Regression Approach to Speech Enhancement Based on Deep Neural Networks@篇paper中特徵�log-power spectral，@是有什N原因�?感x你��~~~
―
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub<#13>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AMt5yT4IvzbJm4ReqatBS2CSkLF1jUR1ks5t_hNngaJpZM4U0uwB>.
from sednn.
JohnChen1124
commented on August 27, 2024
我了解了~所以代碼中的loss function是使用mean absolute error而非mean square error。
在擷取音檔特徵的過程中，將音檔轉換成spectrogram大小值之後有做絕對值，也有取log，但好像沒有取平方，是因為loss function改變而做的調整嗎?感謝您~
from sednn.
qiuqiangkong
commented on August 27, 2024
Loss 是一个值得深入研究的方向。在代码中我们用了log Mel spectrogram，没有取平方。Loss可以选取Lp范数。当p=1时就是abs，当p=2时就是平方。可以尝试调。
…________________________________
From: JohnChen1124 <[email protected]>
Sent: 23 June 2018 14:56:12
To: yongxuUSTC/sednn
Cc: Kong Q Mr (PG/R - Elec Electronic Eng); Comment
Subject: Re: [yongxuUSTC/sednn] 模型�入特徵��}�教 (#13)
我了解了~所以代a中的loss function是使用mean absolute error而非mean square error。
在�X取音�n特徵的^程中，�⒁�nD�Q成spectrogram大小值之後有做^�χ担灿腥log，但好像�]有取平方，是因�loss function改�而做的{整�?
―
You are receiving this because you commented.
Reply to this email directly, view it on GitHub<#13 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AMt5yWlmzUM4kbl0KYdZLr8AArDhb7fNks5t_kj8gaJpZM4U0uwB>.
from sednn.
Nickkk1124
commented on August 27, 2024
真的很感謝您的回覆，您說的log Mel spectrogram與Mel Filter Bank有關係嗎？log Mel spectrogram沒有取平方也是因為PESQ的測量結果嗎？
from sednn.
qiuqiangkong
commented on August 27, 2024
不好意思说错了，我们用的是log spectrogram，不需要Mel。上一封邮件应为：
"
Loss 是一个值得深入研究的方向。在代码中我们用了log spectrogram，没有取平方。Loss可以选取Lp范数。当p=1时就是abs，当p=2时就是平方。可以尝试调。
"
…________________________________
From: Nickkk1124 <[email protected]>
Sent: 24 June 2018 07:18:16
To: yongxuUSTC/sednn
Cc: Kong Q Mr (PG/R - Elec Electronic Eng); Comment
Subject: Re: [yongxuUSTC/sednn] 模型�入特徵��}�教 (#13)
真的很感x您的回覆，您f的log Mel spectrogramcMel Filter Bank有P�S�幔
―
You are receiving this because you commented.
Reply to this email directly, view it on GitHub<#13 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AMt5ydGbRXaNL3LWueV4bCM2WVEhxpqxks5t_y8ogaJpZM4U0uwB>.
from sednn.
Nickkk1124
commented on August 27, 2024
log Mel spectrogram沒有取平方也是因為PESQ的測量結果嗎？還是因為loss改變而跟著改變呢？感謝您～
from sednn.
qiuqiangkong
commented on August 27, 2024
是的，是根据???果?用的。
Get Outlook for Android<https://aka.ms/ghei36>
…________________________________
From: Nickkk1124 <[email protected]>
Sent: Sunday, June 24, 2018 5:35:27 PM
To: yongxuUSTC/sednn
Cc: Kong Q Mr (PG/R - Elec Electronic Eng); Comment
Subject: Re: [yongxuUSTC/sednn] 模型輸入特徵問題請教 (#13)
log Mel spectrogram沒有取平方也是因為PESQ的測量結果嗎？還是因為loss改變而跟著改變呢？感謝您～
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub<#13 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AMt5yRHjKHn0MvXb0MzBJ9a_hrY6z-Izks5t_7_PgaJpZM4U0uwB>.
from sednn.
Related Issues (20)
- 关于打他、
- 关于data_prepare.py中的bug
- about stoi HOT 3
- pretrained model for mixture2clean_dnn? HOT 3
- 增强后语音频谱图问题 HOT 2
- Global name 'librosa' is not defined HOT 5
- 如何使用多种信噪比数据来训练一个model？ HOT 1
- mixture2clean_dnn HOT 1
- PESQ HOT 2
- 你好，请问噪声感知训练部分怎么没有了 HOT 2
- 测试结果不理想 HOT 2
- 训练数据的问题 HOT 1
- 关于噪声估计的问题 HOT 1
- 你好，请问加入噪声感知训练以后loss比不加的时候低了，但是增强后的语音pesq反而变得很差是什么原因 HOT 1
- mixture2clean_dnn_pytorch
- 关于增强后的语音问题 HOT 15
- real_to_complex, 矩阵维度不一致
- pickle.load() HOT 6
- [这个问题困扰我很久，望解答，多谢！]多帧输入，结果出现帧间不连续 HOT 5
- 主观测试不理想
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sednn.