Open JohnChen1124 opened 6 years ago
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 notifications@github.com 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 GitHubhttps://github.com/yongxuUSTC/sednn/issues/13, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AMt5yT4IvzbJm4ReqatBS2CSkLF1jUR1ks5t_hNngaJpZM4U0uwB.
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~
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 notifications@github.com 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,⒁nDQ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 GitHubhttps://github.com/yongxuUSTC/sednn/issues/13#issuecomment-399680167, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AMt5yWlmzUM4kbl0KYdZLr8AArDhb7fNks5t_kj8gaJpZM4U0uwB.
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?
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 notifications@github.com 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PS幔
― You are receiving this because you commented. Reply to this email directly, view it on GitHubhttps://github.com/yongxuUSTC/sednn/issues/13#issuecomment-399732638, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AMt5ydGbRXaNL3LWueV4bCM2WVEhxpqxks5t_y8ogaJpZM4U0uwB.
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~
是的,是根据???果?用的。
Get Outlook for Androidhttps://aka.ms/ghei36
From: Nickkk1124 notifications@github.com 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 GitHubhttps://github.com/yongxuUSTC/sednn/issues/13#issuecomment-399769272, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AMt5yRHjKHn0MvXb0MzBJ9a_hrY6z-Izks5t_7_PgaJpZM4U0uwB.
您好: 非常感謝你們所完成的程式,希望能抽空回答一個小小的問題。模型輸入特徵取完頻譜大小之後有做絕對值,但好像沒有取平方,但在A Regression Approach to Speech Enhancement Based on Deep Neural Networks這篇paper中特徵為log-power spectral,這是有什麼原因嗎?感謝你們~~~