google
Matlab implementation is out of date with modern matlab
Several changes to matlab have made the matlab scripts for CARFAC slightly out of date.
An example of this is the use of wavread and wavwrite which mathworks deprecated a couple years ago in favour of audioread and audiowrite. The example code is also slightly platform specific, but the changes to make it platform agnostic are minimal.
I think SAI_Run.m is close to what you need. It at least has an example of how to compute SAI frames from CARFAC segment outputs. Dick
On Wed, Jul 13, 2022 at 6:54 PM Pitaya-Lychee @.***> wrote:
Hello, it is my honor to receive the code you shared. May I ask which variable in the code I should observe if I want to extract the SAI image of single frame speech in maltab instead of the log-delayed SAI movie? Looking forward to your reply.
— Reply to this email directly, view it on GitHub https://github.com/google/carfac/issues/5#issuecomment-1183866666, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABGW7DD4P2D6RGECHAKTAVDVT5XMRANCNFSM4XOOTAQA . You are receiving this because you are subscribed to this thread.Message ID: @.***>
Oh, sorry,I just noticed this file, but another problem arose. When dealing with log-delay SAI, we set different width and window_width for each layer to constrain the buffer_width, but the SAI_Run.m file requires a sai_struct. Is it also related to the layer_array of each layer in log-delay SAI? Or take another fixed width and window_width? Looking forward to your reply, have a nice day!
------------------ 原始邮件 ------------------ 发件人: "google/carfac" @.>; 发送时间: 2022年7月14日(星期四) 中午1:19 @.>; @.@.>; 主题: Re: [google/carfac] Matlab implementation is out of date with modern matlab (#5)
I think SAI_Run.m is close to what you need. It at least has an example of how to compute SAI frames from CARFAC segment outputs. Dick
On Wed, Jul 13, 2022 at 6:54 PM Pitaya-Lychee @.***> wrote:
> Hello, it is my honor to receive the code you shared. May I ask which > variable in the code I should observe if I want to extract the SAI image of > single frame speech in maltab instead of the log-delayed SAI movie? Looking > forward to your reply. > > — > Reply to this email directly, view it on GitHub > <https://github.com/google/carfac/issues/5#issuecomment-1183866666>, or > unsubscribe > <https://github.com/notifications/unsubscribe-auth/ABGW7DD4P2D6RGECHAKTAVDVT5XMRANCNFSM4XOOTAQA> > . > You are receiving this because you are subscribed to this thread.Message > ID: @.***> >
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>
I don't recall and don't have the code in front of me right now, but I believe there's another file by that one called something like SAI_hacking.m, which might give you a good example of how to use it. Dick
On Thu, Jul 14, 2022, 12:51 AM Pitaya-Lychee @.***> wrote:
Oh, sorry,I just noticed this file, but another problem arose. When dealing with log-delay SAI, we set different width and window_width for each layer to constrain the buffer_width, but the SAI_Run.m file requires a sai_struct. Is it also related to the layer_array of each layer in log-delay SAI? Or take another fixed width and window_width? Looking forward to your reply, have a nice day!
------------------ 原始邮件 ------------------ 发件人: "google/carfac" @.>; 发送时间: 2022年7月14日(星期四) 中午1:19 @.>; @.@.>; 主题: Re: [google/carfac] Matlab implementation is out of date with modern matlab (#5)
I think SAI_Run.m is close to what you need. It at least has an example of how to compute SAI frames from CARFAC segment outputs. Dick
On Wed, Jul 13, 2022 at 6:54 PM Pitaya-Lychee @.***> wrote:
> Hello, it is my honor to receive the code you shared. May I ask which > variable in the code I should observe if I want to extract the SAI image of > single frame speech in maltab instead of the log-delayed SAI movie? Looking > forward to your reply. > > — > Reply to this email directly, view it on GitHub > <https://github.com/google/carfac/issues/5#issuecomment-1183866666>, or > unsubscribe > < https://github.com/notifications/unsubscribe-auth/ABGW7DD4P2D6RGECHAKTAVDVT5XMRANCNFSM4XOOTAQA>
> . > You are receiving this because you are subscribed to this thread.Message > ID: @.***> >
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>
— Reply to this email directly, view it on GitHub https://github.com/google/carfac/issues/5#issuecomment-1184116464, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABGW7DCH6OZYO4WNRGLEW2LVT7BITANCNFSM4XOOTAQA . You are receiving this because you commented.Message ID: @.***>