Training LSTM network on raw audio data?












0












$begingroup$


I am trying to give an LSTM network raw audio data in forms of samples (44100 / second). Samples are defined in the [-1,1] value space. Currently I am giving it one sample for the Y values and the past N samples for X values.



Due to the fact that there are a lot of samples per second, you can see how it easily runs out of memory and the ability to give it large audio files (basically storing 16 samples for every sample given, for example will yield a very large dataset quickly).



I can post the code as well if necessary, however, I am only trying to figure out if my approach is correct. Training the data on a sine wave for example yields only values of 1, and the loss rate doesn't seem to go down much, so I am suspecting the way I am giving the network data is wrong. Is giving the past N samples to predict the current sample a good approach? I am pretty new in the AI field.










share|improve this question







New contributor




Space Ghost is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.







$endgroup$

















    0












    $begingroup$


    I am trying to give an LSTM network raw audio data in forms of samples (44100 / second). Samples are defined in the [-1,1] value space. Currently I am giving it one sample for the Y values and the past N samples for X values.



    Due to the fact that there are a lot of samples per second, you can see how it easily runs out of memory and the ability to give it large audio files (basically storing 16 samples for every sample given, for example will yield a very large dataset quickly).



    I can post the code as well if necessary, however, I am only trying to figure out if my approach is correct. Training the data on a sine wave for example yields only values of 1, and the loss rate doesn't seem to go down much, so I am suspecting the way I am giving the network data is wrong. Is giving the past N samples to predict the current sample a good approach? I am pretty new in the AI field.










    share|improve this question







    New contributor




    Space Ghost is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
    Check out our Code of Conduct.







    $endgroup$















      0












      0








      0





      $begingroup$


      I am trying to give an LSTM network raw audio data in forms of samples (44100 / second). Samples are defined in the [-1,1] value space. Currently I am giving it one sample for the Y values and the past N samples for X values.



      Due to the fact that there are a lot of samples per second, you can see how it easily runs out of memory and the ability to give it large audio files (basically storing 16 samples for every sample given, for example will yield a very large dataset quickly).



      I can post the code as well if necessary, however, I am only trying to figure out if my approach is correct. Training the data on a sine wave for example yields only values of 1, and the loss rate doesn't seem to go down much, so I am suspecting the way I am giving the network data is wrong. Is giving the past N samples to predict the current sample a good approach? I am pretty new in the AI field.










      share|improve this question







      New contributor




      Space Ghost is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.







      $endgroup$




      I am trying to give an LSTM network raw audio data in forms of samples (44100 / second). Samples are defined in the [-1,1] value space. Currently I am giving it one sample for the Y values and the past N samples for X values.



      Due to the fact that there are a lot of samples per second, you can see how it easily runs out of memory and the ability to give it large audio files (basically storing 16 samples for every sample given, for example will yield a very large dataset quickly).



      I can post the code as well if necessary, however, I am only trying to figure out if my approach is correct. Training the data on a sine wave for example yields only values of 1, and the loss rate doesn't seem to go down much, so I am suspecting the way I am giving the network data is wrong. Is giving the past N samples to predict the current sample a good approach? I am pretty new in the AI field.







      keras






      share|improve this question







      New contributor




      Space Ghost is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.











      share|improve this question







      New contributor




      Space Ghost is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      share|improve this question




      share|improve this question






      New contributor




      Space Ghost is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      asked 15 hours ago









      Space GhostSpace Ghost

      1




      1




      New contributor




      Space Ghost is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.





      New contributor





      Space Ghost is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






      Space Ghost is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






















          0






          active

          oldest

          votes












          Your Answer








          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "557"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: false,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: null,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });






          Space Ghost is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f49324%2ftraining-lstm-network-on-raw-audio-data%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes








          Space Ghost is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          Space Ghost is a new contributor. Be nice, and check out our Code of Conduct.













          Space Ghost is a new contributor. Be nice, and check out our Code of Conduct.












          Space Ghost is a new contributor. Be nice, and check out our Code of Conduct.
















          Thanks for contributing an answer to Data Science Stack Exchange!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          Use MathJax to format equations. MathJax reference.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f49324%2ftraining-lstm-network-on-raw-audio-data%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          How to label and detect the document text images

          Vallis Paradisi

          Tabula Rosettana