• State
  • Locked Locked
  • Replies 4 replies
  • Subscribers 99 subscribers
  • Views 615 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

running matlab code with c6713

kushant vyas
Prodigy 70 points

i want to implement speech separation on c6713 kit. i have two prerecorded .wav files and matlab code that works on them to give two separated signals. how to implement this on dsp???

i tried to convert matlab functions in C using matlab coder, but the problem is that my program is not realtime, that is it does not work sample by sample. it takes all the samples of both the files and then process them.(is it true that your c program must take a sample from codec then algorithm runs and waits for the next sample?)

secondly, i am not sure how to use pre recorded files with dsp. Since, wavread function in matlab is not allowed for conversion in C.

please point me in right direction. thank you in advance. 

  • 0
    TI__Mastermind 43955 points

    Hi Kushant,

    MATLAB is not provided by TI . In this forum, we do not handle queries related to Matlab. Usually Matlab queries will get posted on CCS forum.

    If needed I can move this post to CCS.

    The DSKC6713 will be supplied with some example packages which sets development environment to do experiments, develop a new code or modify the existing code and test it on target, e.t.c. You can get some hands-on on programming and then try implementing in C equivalent to the matlab function. OR

    Search in TI WIKI pages for any suitable audio codec which runs on C67+ platforms and that can be utilised for your project. http://processors.wiki.ti.com/index.php/How_do_I_Integrate_new_codecs_into_DVSDK

    http://processors.wiki.ti.com/index.php/Codec_FAQ

     

    The following TI Wiki link and it's sublinks on Student guide, workshops might be helpful to you.

    http://processors.wiki.ti.com/index.php/TMS320C6x1x_DSP_Integration_Workshop

     

    Regards,

    Shankari

  • 0 in reply to Shankari G
    Prodigy 70 points

    thank you so much for your reply...I will modify my question.

    i want to implement speech separation. two speakers speak simultaneously and two microphones record this. these recordings are to be processed by dsp.

    i have converted my algorithm into C. but this requires simultaneously two speech recordings. my question is: is it possible to use two microphone input in DSP? If yes how?

    secondly, all the examples show that a sample is taken from codec and algorithm works before the next sample arrives. My algorthm requires all the samples of both files to calculate the separated speech signals (it is not realtime). how can I implement this?

    please help me.

  • 0 in reply to kushant vyas
    Prodigy 70 points

    please answer my question...

    i m waiting for reply.

  • 0 in reply to kushant vyas
    TI__Guru* 84110 points

    Kushant,

    Firstly, please look at the 6713_dsk_schem schematic file that the vendor provides for the DSK. The last page has the audio components and shows the microphone in put and the stereo Line In connections. These are what you have available without adding to the DSK. Can you make these work for your application?

    Secondly, please go to the TI Wiki Pages and search for "C6x1x workshop" (no quotes) to find the C6713 training course. You will need to go through this material, hopefully you will go through the labs as you work through the archived Student Guide. You need to learn how to write code for the DSP, and this material explains that process, especially the types of things you want to do for this large buffer of data.

    Regards,
    RandyP