0
$\begingroup$

I am dealing with a problem about classifying bird species through analysing MFCCs. I already built a dataset with 13 MFCCs for two kinds of birds. And I trained the data with Naive Bayes & KNN model. However, when I tried the model with prediction of third bird species, it is classified as the one of the two species. I am wondering how can I achieve to predict unknown species as unknowns? And I know my existing classification model may not work. So, what kind of model might be helpful? Does SSL useful in my case? Or treat these unknowns as outliers? But how can that be applied in MFCC?

$\endgroup$
0
$\begingroup$

If you want to predict wether a bird is a bird of one of your two classes or unknown you need three classes: $[bird A, bird B, unknown]$. For the unknown class you need data from birds which are neither $bird A$ nor $bird B$. You should make sure the number of rows for each of the three classes is roughly the same.

If you don't have data of birds which are neither $bird A$ nor $bird B$ you can use anomaly detection to detect wether a bird is $unknown$ before predicting if it is $class A$ or $class B$.

$\endgroup$
3
  • $\begingroup$ Hi Tim @Tim, so is there any other way besides enlarging my training dataset? Do I have to create a new unknown class for storing the unknown data? As my prediction data is from my microphone input, so it could be the sound from any species or even human voices. And how could I deal with it? $\endgroup$ – 夏思阳 Aug 23 '20 at 10:25
  • $\begingroup$ @夏思阳 Anomaly detection works without enlarging your dataset. Besides that I don't know of any other way. If your input can be the voice of a human, you can use data from human voices in your unknown class. $\endgroup$ – Tim von Känel Aug 23 '20 at 11:14
  • $\begingroup$ @ Tim, thanks I will try that $\endgroup$ – 夏思阳 Aug 23 '20 at 11:34
0
$\begingroup$

I don't have much experience with MFCCs but you could always take inspiration from image processing and build a siamese network like model that would give you a distance metric between your sample and that if your distinct classes.

you could then pick the highest distance metric and set a lower threshold to classify it as unknown if none of the existing classes give you a high enough similarity.

After which all you got to do is analyze the unknown sample and create a jew class.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.