Process melspectrograms with convolutional neural network2019 Community Moderator ElectionNeural network with flexible number of inputs?Convolutional Neural Network not learning EEG dataHow does a convolutional ply differ from an ordinary convolutional network?python - What is the format of the WAV file for a Text to Speech Neural Network?Invalid Argument Error when running simple Convolutional Neural NetworkMulti-inputs Convolutional Neural Network takes different number of imagesWhat is the effect of highly correlated data on a Convolutional Neural Network?Print the prediction of convolutional neural networkMulti-input Convolutional Neural Network for Images Classificationprocess images with spiking neural network
How do we improve the relationship with a client software team that performs poorly and is becoming less collaborative?
Can I interfere when another PC is about to be attacked?
Writing rule which states that two causes for the same superpower is bad writing
Is it tax fraud for an individual to declare non-taxable revenue as taxable income? (US tax laws)
Why linear maps act like matrix multiplication?
How do I create uniquely male characters?
How old can references or sources in a thesis be?
What is the command to reset a PC without deleting any files
Dragon forelimb placement
Why is the design of haulage companies so “special”?
Is it possible to rebuild the bike frame (to make it lighter) by welding aluminum tubes
Email Account under attack (really) - anything I can do?
Motorized valve interfering with button?
Underlining section titles
Type 1 Error & Type 2 Error's pregnancy test analogy: is it legit?
Is the language p and n are natural numbers and there's no prime number in [p,p+n] belongs to NP class?
Why don't electron-positron collisions release infinite energy?
How much RAM could one put in a typical 80386 setup?
The use of multiple foreign keys on same column in SQL Server
Explain the parameters before and after @ in the terminal prompt
Can I make popcorn with any corn?
What do the dots in this tr command do: tr .............A-Z A-ZA-Z <<< "JVPQBOV" (with 13 dots)
XeLaTeX and pdfLaTeX ignore hyphenation
Approximately how much travel time was saved by the opening of the Suez Canal in 1869?
Process melspectrograms with convolutional neural network
2019 Community Moderator ElectionNeural network with flexible number of inputs?Convolutional Neural Network not learning EEG dataHow does a convolutional ply differ from an ordinary convolutional network?python - What is the format of the WAV file for a Text to Speech Neural Network?Invalid Argument Error when running simple Convolutional Neural NetworkMulti-inputs Convolutional Neural Network takes different number of imagesWhat is the effect of highly correlated data on a Convolutional Neural Network?Print the prediction of convolutional neural networkMulti-input Convolutional Neural Network for Images Classificationprocess images with spiking neural network
$begingroup$
I am trying to do audio classification with a convolutional neural network. There are six classes. With librosa, I have created melspectrograms for the one second long .wav audio files. It returned 640x480 .jpg files.
My question is now how to proceed with the input, since I think it is too large as input for the network. If so, what would an adequate resolution be? Something around 60x60? Does it even have to be quadratic?
Options from my perspective:
- Re-encode melspectrograms from librosa with smaller resolution
- Use cv2 and simply do a cv2.resize() before passing it to the input layer.
- Leave the resolution untouched, and introduce more convolutional layers.
- ?
python audio-recognition
asked Mar 8 at 12:14
harrisonfooordharrisonfooord
62
$endgroup$
bumped to the homepage by Community♦ 3 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
add a comment |
$begingroup$
I am trying to do audio classification with a convolutional neural network. There are six classes. With librosa, I have created melspectrograms for the one second long .wav audio files. It returned 640x480 .jpg files.
My question is now how to proceed with the input, since I think it is too large as input for the network. If so, what would an adequate resolution be? Something around 60x60? Does it even have to be quadratic?
Options from my perspective:
- Re-encode melspectrograms from librosa with smaller resolution
- Use cv2 and simply do a cv2.resize() before passing it to the input layer.
- Leave the resolution untouched, and introduce more convolutional layers.
- ?
python audio-recognition
asked Mar 8 at 12:14
harrisonfooordharrisonfooord
62
$endgroup$
bumped to the homepage by Community♦ 3 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
add a comment |
$begingroup$
I am trying to do audio classification with a convolutional neural network. There are six classes. With librosa, I have created melspectrograms for the one second long .wav audio files. It returned 640x480 .jpg files.
My question is now how to proceed with the input, since I think it is too large as input for the network. If so, what would an adequate resolution be? Something around 60x60? Does it even have to be quadratic?
Options from my perspective:
- Re-encode melspectrograms from librosa with smaller resolution
- Use cv2 and simply do a cv2.resize() before passing it to the input layer.
- Leave the resolution untouched, and introduce more convolutional layers.
- ?
python audio-recognition
asked Mar 8 at 12:14
harrisonfooordharrisonfooord
62
$endgroup$
I am trying to do audio classification with a convolutional neural network. There are six classes. With librosa, I have created melspectrograms for the one second long .wav audio files. It returned 640x480 .jpg files.
My question is now how to proceed with the input, since I think it is too large as input for the network. If so, what would an adequate resolution be? Something around 60x60? Does it even have to be quadratic?
Options from my perspective:
- Re-encode melspectrograms from librosa with smaller resolution
- Use cv2 and simply do a cv2.resize() before passing it to the input layer.
- Leave the resolution untouched, and introduce more convolutional layers.
- ?
python audio-recognition
python audio-recognition
asked Mar 8 at 12:14
harrisonfooordharrisonfooord
62
asked Mar 8 at 12:14
harrisonfooordharrisonfooord
62
asked Mar 8 at 12:14
harrisonfooordharrisonfooord
62
asked Mar 8 at 12:14
harrisonfooordharrisonfooord
62
asked Mar 8 at 12:14
harrisonfooordharrisonfooord
62
62
bumped to the homepage by Community♦ 3 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
bumped to the homepage by Community♦ 3 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
Leave the resolution untouched, and introduce more convolutional
layers.
This should be the next step. Two primary reasons for it :
- This should reduce number of trainable parameters
- Model can learn more abstract features
answered Mar 8 at 13:19
Shamit VermaShamit Verma
1,4291214
$endgroup$
add a comment |
Your Answer
StackExchange.ifUsing("editor", function ()
return StackExchange.using("mathjaxEditing", function ()
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
);
);
, "mathjax-editing");
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
);
);
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f46926%2fprocess-melspectrograms-with-convolutional-neural-network%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
Leave the resolution untouched, and introduce more convolutional
layers.
This should be the next step. Two primary reasons for it :
- This should reduce number of trainable parameters
- Model can learn more abstract features
answered Mar 8 at 13:19
Shamit VermaShamit Verma
1,4291214
$endgroup$
add a comment |
$begingroup$
Leave the resolution untouched, and introduce more convolutional
layers.
This should be the next step. Two primary reasons for it :
- This should reduce number of trainable parameters
- Model can learn more abstract features
answered Mar 8 at 13:19
Shamit VermaShamit Verma
1,4291214
$endgroup$
add a comment |
$begingroup$
Leave the resolution untouched, and introduce more convolutional
layers.
This should be the next step. Two primary reasons for it :
- This should reduce number of trainable parameters
- Model can learn more abstract features
answered Mar 8 at 13:19
Shamit VermaShamit Verma
1,4291214
$endgroup$
Leave the resolution untouched, and introduce more convolutional
layers.
This should be the next step. Two primary reasons for it :
- This should reduce number of trainable parameters
- Model can learn more abstract features
answered Mar 8 at 13:19
Shamit VermaShamit Verma
1,4291214
answered Mar 8 at 13:19
Shamit VermaShamit Verma
1,4291214
answered Mar 8 at 13:19
Shamit VermaShamit Verma
1,4291214
answered Mar 8 at 13:19
Shamit VermaShamit Verma
1,4291214
1,4291214
add a comment |
add a comment |
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.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f46926%2fprocess-melspectrograms-with-convolutional-neural-network%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
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
