Menu

Home

Daniel Povey

Discussion

  • Vaibhav

    Vaibhav - 2018-07-03

    Hi

    I wanted to know that where i can found the script to extract pitch features only .
    I know there is script for mfcc + pitch and plp + pitch features .
    But i am unable to find the script to extract only pitch features .

    Thanks

     
    • Daniel Povey

      Daniel Povey - 2018-07-03

      kaldi doesn't live on sourceforge anymore.
      There isn't a script in steps/, but you can easily figure out how to
      write one if you understand Kaldi I/O mechanisms, with reference to
      the existing scripts.

      On Tue, Jul 3, 2018 at 6:00 AM, Vaibhav
      ervaibhavkumar@users.sourceforge.net wrote:

      Hi

      I wanted to know that where i can found the script to extract pitch features
      only .
      I know there is script for mfcc + pitch and plp + pitch features .
      But i am unable to find the script to extract only pitch features .

      Thanks


      Sent from sourceforge.net because you indicated interest in
      https://sourceforge.net/p/kaldi/wiki/Home/

      To unsubscribe from further messages, please visit
      https://sourceforge.net/auth/subscriptions/

       
  • Vaibhav

    Vaibhav - 2018-07-04

    Ok Thanks for your help sir

     
  • Vaibhav

    Vaibhav - 2018-07-04

    I am facing one more issue sir

    I had run mfcc + pitch script with multiple available options
    --add-pov-feature , --add-normalized-pitch etc .
    but i am getting a WER % of about 55-60 %
    Please suggest what can i do ?

    Thanks

     
    • creatorscan

      creatorscan - 2018-07-04

      Hi,
      If you are using a standard speech database, can you mention it. Its easy
      to compare.

      On Wed, 4 Jul 2018 at 01:46, Vaibhav ervaibhavkumar@users.sourceforge.net
      wrote:

      I am facing one more issue sir

      I had run mfcc + pitch script with multiple available options
      --add-pov-feature , --add-normalized-pitch etc .
      but i am getting a WER % of about 55-60 %
      Please suggest what can i do ?

      Thanks


      Sent from sourceforge.net because you indicated interest in <
      https://sourceforge.net/p/kaldi/wiki/Home/>

      To unsubscribe from further messages, please visit <
      https://sourceforge.net/auth/subscriptions/>

      --
      Peace,
      Murali Karthick Baskar

       
  • Vaibhav

    Vaibhav - 2018-07-04

    i am not using any standard database .
    I am having my own dataset of Punjabi language which is tonal language . So i thought it would be good to add pitch features with mfcc but the results are not good with or without pitch features .
    What can i do ?

     
    • rohit kodali

      rohit kodali - 2018-07-04

      Hi vaibhav,

      What is your dataset size and how many speakers, what is your training and
      testing vocabulary. Which model you have used for testing.

      To answer about wer we need to know these atleast. And how many phones in
      your lexicon for punjabi

      On Wed, 4 Jul 2018, 11:47 am Vaibhav, ervaibhavkumar@users.sourceforge.net
      wrote:

      i am not using any standard database .
      I am having my own dataset of Punjabi language which is tonal language .
      So i thought it would be good to add pitch features with mfcc but the
      results are not good with or without pitch features .
      What can i do ?


      Sent from sourceforge.net because you indicated interest in
      https://sourceforge.net/p/kaldi/wiki/Home/

      To unsubscribe from further messages, please visit
      https://sourceforge.net/auth/subscriptions/

       
  • Vaibhav

    Vaibhav - 2018-07-04

    28 speakers for training and 4 for testing
    90 minutes training data .
    vocab size is 1400 words training .
    I had trained using mono , tri1 , tri2 , tri3 and sgmm models but all are giving wer in range 55-65

     
    • rohit kodali

      rohit kodali - 2018-07-04
      1. is the testing speakers are available in training or different
      2. What is your phone set size
      3. are the testing words exist in the the 1400 words

      and i don't think we get better accuracy with just 90 minutes of indian
      languages data

      On Wed, Jul 4, 2018 at 12:13 PM Vaibhav ervaibhavkumar@users.sourceforge.net wrote:

      28 speakers for training and 4 for testing
      90 minutes training data .
      vocab size is 1400 words training .
      I had trained using mono , tri1 , tri2 , tri3 and sgmm models but all are
      giving wer in range 55-65


      Sent from sourceforge.net because you indicated interest in
      https://sourceforge.net/p/kaldi/wiki/Home/

      To unsubscribe from further messages, please visit
      https://sourceforge.net/auth/subscriptions/

      --
      Best regards,
      K.Rohith Gowtham

       
  • Vaibhav

    Vaibhav - 2018-07-04

    testing speakers are different
    phone set size = 170
    Yes , testing words exist in the the 1400 words

    What can be done ?
    Also i had tried training and testing on same speakers but again the WER was in range 60-75 %

     

    Last edit: Vaibhav 2018-07-04
    • rohit kodali

      rohit kodali - 2018-07-04

      170 phonemes for punjabi language i can see a max of 45 phonemes including
      silence for this ( if you use position dependent it will be 140 max), how
      you got 170 phone set. if you really have 170 phonemes then the phonetic
      coverage is too low for any phoneme in the training set.

      On Wed, Jul 4, 2018 at 12:24 PM Vaibhav ervaibhavkumar@users.sourceforge.net wrote:

      testing speakers are different
      phone set size = 170
      Yes , testing words exist in the the 1400 words


      Sent from sourceforge.net because you indicated interest in
      https://sourceforge.net/p/kaldi/wiki/Home/

      To unsubscribe from further messages, please visit
      https://sourceforge.net/auth/subscriptions/

      --
      Best regards,
      K.Rohith Gowtham

       
  • Vaibhav

    Vaibhav - 2018-07-04

    I saw wrong file Sorry .
    It was 40

    How can i improve accuracy ?

     
    • rohit kodali

      rohit kodali - 2018-07-04

      Add More data from more speakers and get good phone tic coverage

      On Wed, 4 Jul 2018, 1:33 pm Vaibhav, ervaibhavkumar@users.sourceforge.net
      wrote:

      I saw wrong file Sorry .
      It was 40

      How can i improve accuracy ?

      Sent from sourceforge.net because you indicated interest in
      https://sourceforge.net/p/kaldi/wiki/Home/

      To unsubscribe from further messages, please visit
      https://sourceforge.net/auth/subscriptions/

       
      • Daniel Povey

        Daniel Povey - 2018-07-04

        Rohit: thanks for responding. For your guys' info, kaldi-help is the
        primary location for these discussions, see kaldi-asr.org/forums.html.
        There may be forums for Indian users of Kaldi too, which I am not
        aware of, and these, if they exist, would very very suitable for new
        users like Vaibhav.

        On Wed, Jul 4, 2018 at 4:34 AM, rohit kodali
        rohitgowtham@users.sourceforge.net wrote:

        Add More data from more speakers and get good phone tic coverage

        On Wed, 4 Jul 2018, 1:33 pm Vaibhav, ervaibhavkumar@users.sourceforge.net
        wrote:

        I saw wrong file Sorry .
        It was 40

        How can i improve accuracy ?

        Sent from sourceforge.net because you indicated interest in
        https://sourceforge.net/p/kaldi/wiki/Home/

        To unsubscribe from further messages, please visit
        https://sourceforge.net/auth/subscriptions/


        Sent from sourceforge.net because you indicated interest in
        https://sourceforge.net/p/kaldi/wiki/Home/

        To unsubscribe from further messages, please visit
        https://sourceforge.net/auth/subscriptions/

         
        • rohit kodali

          rohit kodali - 2018-07-04

          Hi dan,

          I actively follow kaldi forums. I don't think we have anything specially
          for indian or any other tonal languages, but if we have something for it i
          would like to help the guys who are researching into them. I have been
          doing on these from kaldi beginning (proud to say first comment on kaldi is
          mine when released), tried almost all experiments on tonal languages on
          huge datasets collected by ourselves.

          On Wed, 4 Jul 2018, 11:50 pm Daniel Povey, danielpovey@users.sourceforge.net wrote:

          Rohit: thanks for responding. For your guys' info, kaldi-help is the
          primary location for these discussions, see kaldi-asr.org/forums.html.
          There may be forums for Indian users of Kaldi too, which I am not
          aware of, and these, if they exist, would very very suitable for new
          users like Vaibhav.

          On Wed, Jul 4, 2018 at 4:34 AM, rohit kodali
          rohitgowtham@users.sourceforge.net wrote:

          Add More data from more speakers and get good phone tic coverage

          On Wed, 4 Jul 2018, 1:33 pm Vaibhav, ervaibhavkumar@users.sourceforge.net
          wrote:

          I saw wrong file Sorry .
          It was 40

          How can i improve accuracy ?

          Sent from sourceforge.net because you indicated interest in
          https://sourceforge.net/p/kaldi/wiki/Home/

          To unsubscribe from further messages, please visit
          https://sourceforge.net/auth/subscriptions/


          Sent from sourceforge.net because you indicated interest in
          https://sourceforge.net/p/kaldi/wiki/Home/

          To unsubscribe from further messages, please visit
          https://sourceforge.net/auth/subscriptions/


          Sent from sourceforge.net because you indicated interest in
          https://sourceforge.net/p/kaldi/wiki/Home/

          To unsubscribe from further messages, please visit
          https://sourceforge.net/auth/subscriptions/

           
          • Daniel Povey

            Daniel Povey - 2018-07-04

            Cool.
            I know that in China they have various dedicated lists.
            If you were to start one for Kaldi researchers in India it might be
            helpful. If you do, try to set it up so the archives are searchable
            (like kaldi-help) so that people can find it from google.
            Dan

            On Wed, Jul 4, 2018 at 2:34 PM, rohit kodali
            rohitgowtham@users.sourceforge.net wrote:

            Hi dan,

            I actively follow kaldi forums. I don't think we have anything specially
            for indian or any other tonal languages, but if we have something for it i
            would like to help the guys who are researching into them. I have been
            doing on these from kaldi beginning (proud to say first comment on kaldi is
            mine when released), tried almost all experiments on tonal languages on
            huge datasets collected by ourselves.

            On Wed, 4 Jul 2018, 11:50 pm Daniel Povey, danielpovey@users.sourceforge.net
            wrote:

            Rohit: thanks for responding. For your guys' info, kaldi-help is the
            primary location for these discussions, see kaldi-asr.org/forums.html.
            There may be forums for Indian users of Kaldi too, which I am not
            aware of, and these, if they exist, would very very suitable for new
            users like Vaibhav.

            On Wed, Jul 4, 2018 at 4:34 AM, rohit kodali
            rohitgowtham@users.sourceforge.net wrote:

            Add More data from more speakers and get good phone tic coverage

            On Wed, 4 Jul 2018, 1:33 pm Vaibhav, ervaibhavkumar@users.sourceforge.net
            wrote:

            I saw wrong file Sorry .
            It was 40

            How can i improve accuracy ?

            Sent from sourceforge.net because you indicated interest in
            https://sourceforge.net/p/kaldi/wiki/Home/

            To unsubscribe from further messages, please visit
            https://sourceforge.net/auth/subscriptions/


            Sent from sourceforge.net because you indicated interest in
            https://sourceforge.net/p/kaldi/wiki/Home/

            To unsubscribe from further messages, please visit
            https://sourceforge.net/auth/subscriptions/


            Sent from sourceforge.net because you indicated interest in
            https://sourceforge.net/p/kaldi/wiki/Home/

            To unsubscribe from further messages, please visit
            https://sourceforge.net/auth/subscriptions/


            Sent from sourceforge.net because you indicated interest in
            https://sourceforge.net/p/kaldi/wiki/Home/

            To unsubscribe from further messages, please visit
            https://sourceforge.net/auth/subscriptions/

             
            • rohit kodali

              rohit kodali - 2018-07-04

              Sure, I will do that.

              On Thu, 5 Jul 2018, 12:14 am Daniel Povey, danielpovey@users.sourceforge.net wrote:

              Cool.
              I know that in China they have various dedicated lists.
              If you were to start one for Kaldi researchers in India it might be
              helpful. If you do, try to set it up so the archives are searchable
              (like kaldi-help) so that people can find it from google.
              Dan

              On Wed, Jul 4, 2018 at 2:34 PM, rohit kodali
              rohitgowtham@users.sourceforge.net wrote:

              Hi dan,

              I actively follow kaldi forums. I don't think we have anything specially
              for indian or any other tonal languages, but if we have something for it i
              would like to help the guys who are researching into them. I have been
              doing on these from kaldi beginning (proud to say first comment on kaldi is
              mine when released), tried almost all experiments on tonal languages on
              huge datasets collected by ourselves.

              On Wed, 4 Jul 2018, 11:50 pm Daniel Povey,
              danielpovey@users.sourceforge.net
              wrote:

              Rohit: thanks for responding. For your guys' info, kaldi-help is the
              primary location for these discussions, see kaldi-asr.org/forums.html.
              There may be forums for Indian users of Kaldi too, which I am not
              aware of, and these, if they exist, would very very suitable for new
              users like Vaibhav.

              On Wed, Jul 4, 2018 at 4:34 AM, rohit kodali
              rohitgowtham@users.sourceforge.net wrote:

              Add More data from more speakers and get good phone tic coverage

              On Wed, 4 Jul 2018, 1:33 pm Vaibhav, ervaibhavkumar@users.sourceforge.net
              wrote:

              I saw wrong file Sorry .
              It was 40

              How can i improve accuracy ?

              Sent from sourceforge.net because you indicated interest in
              https://sourceforge.net/p/kaldi/wiki/Home/

              To unsubscribe from further messages, please visit
              https://sourceforge.net/auth/subscriptions/


              Sent from sourceforge.net because you indicated interest in
              https://sourceforge.net/p/kaldi/wiki/Home/

              To unsubscribe from further messages, please visit
              https://sourceforge.net/auth/subscriptions/


              Sent from sourceforge.net because you indicated interest in
              https://sourceforge.net/p/kaldi/wiki/Home/

              To unsubscribe from further messages, please visit
              https://sourceforge.net/auth/subscriptions/


              Sent from sourceforge.net because you indicated interest in
              https://sourceforge.net/p/kaldi/wiki/Home/

              To unsubscribe from further messages, please visit
              https://sourceforge.net/auth/subscriptions/


              Sent from sourceforge.net because you indicated interest in
              https://sourceforge.net/p/kaldi/wiki/Home/

              To unsubscribe from further messages, please visit
              https://sourceforge.net/auth/subscriptions/

               
  • Vaibhav

    Vaibhav - 2018-07-05

    Thanks for helping out
    Is there any other thing i can try to reduce WER % ?

     
  • shashi

    shashi - 2018-09-10

    Hello,
    Can Any one provide the limitations for kaldi usage such as, how it works on realtime data?
    can we stream data for 6-8 hours?
    speaking recoginization based on time window?

     
    • Daniel Povey

      Daniel Povey - 2018-09-10

      see kaldi-asr.org/forums.html for how to ask questions, but your questions
      are very unclear.

      On Mon, Sep 10, 2018 at 7:12 AM shashi shashi1020@users.sourceforge.net
      wrote:

      Hello,
      Can Any one provide the limitations for kaldi usage such as, how it works
      on realtime data?
      can we stream data for 6-8 hours?
      speaking recoginization based on time window?


      Sent from sourceforge.net because you indicated interest in
      https://sourceforge.net/p/kaldi/wiki/Home/

      To unsubscribe from further messages, please visit
      https://sourceforge.net/auth/subscriptions/

       
      • shashi

        shashi - 2018-09-11

        Sorry Dan..
        I'll make my question clear to you.

        Using kaldi is it possible to translate a stram of 6-8 hours audio into text?

         
        • Daniel Povey

          Daniel Povey - 2018-09-11

          you'd want to break it up into smaller pieces, like 15 segments as the
          decoder doesn't handle too-long segments, but thaat's trivial.

          On Tue, Sep 11, 2018 at 3:43 AM shashi shashi1020@users.sourceforge.net
          wrote:

          Sorry Dan..
          I'll make my question clear to you.

          Using kaldi is it possible to translate a stram of 6-8 hours audio into
          text?


          Sent from sourceforge.net because you indicated interest in
          https://sourceforge.net/p/kaldi/wiki/Home/

          To unsubscribe from further messages, please visit
          https://sourceforge.net/auth/subscriptions/

           

Log in to post a comment.

Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.