d4r3topk / comparing-audio-files-python Goto Github PK

Because of the changes in version 0.6.0 of librosa, import librosa.display is required for librosa.display.specshow() to work.

import librosa.display
import matplotlib.pyplot as plt
from scipy.spatial.distance import euclidean,mahalanobis
from dtw import dtw

dist, _, cost, path = dtw(mfcc1.T, mfcc2.T, dist=euclidean)

This is not really an issue,but a doubt rather.

It's mentioned as a comment that the dist value for similar audios should be 0 or close to 0? If that's what you meant.

I am doing a speech project in which I'm comparing the similarity between audios. Basically I have a bunch of phoneme recordings from the same voice. Some of them sound similar and some of them don't. So I am using this dist measure to quantify that similarity. And based on what i've observed so far with the samples I have,a dist value of anything less than 180 is holding true for similar sounding phoneme recordings and greater than 180 for the dissimilar ones.
And it's never or not even close to zero.

Can I use this condition to compare the similarities? Please let me know. Thanks in advance.

Could you update this: https://github.com/d4r3topk/comparing-audio-files-python/blob/master/mfcc.py

It's addressed here: pollen-robotics/dtw@307fe72

The original issue is here: pollen-robotics/dtw#18

This would be a huge help for folks who go through some of your snippets