Skip to main content
OverflowAI is here! AI power for your Stack Overflow for Teams knowledge community. Learn more
7 votes

Is there a public repository of labeled sound files coming from an industrial area?

Freesound is a repository of sound files categorised by user-defined tags. Through those, you can spot what other users have labeled industrial sounds but be prepared that some of those might be ...
A_A's user avatar
  • 10.7k
5 votes

System classification: unit-time delay

You are right that a distributed system could be "something like a transmission line". Note that the system $$y(t)=x(t-T)\tag{1}$$ is a simple model of a transmission line, where just a frequency-...
Matt L.'s user avatar
  • 90.3k
4 votes

Feature extraction for sound classification

Non-verbal Audio (let alone environmental) seems to be the little brother to main stream machine learning media types like images, speech, text. To answer your question is it possible to train a ...
beeCwright's user avatar
3 votes

MFCC feature vector from wav file

Have a look at these two python libraries that provide a number of audio features easily from WAV files, including MFCC. Librosa: MFCC docs, github Madmom: MFCC docs, github Good luck!
ruoho ruotsi's user avatar
  • 1,770
3 votes

Feature extraction for sound classification

Here is a solution for sound classification for 10 classes: dog barking, car horn, children playing etc. It is based on tensorflow library using neural networks. Features are extracted by converting ...
abggcv's user avatar
  • 151
3 votes
Accepted

How we calculate Precision-Recall Curve?

You're right. When you just have a single precision and a single recall value, you get a precision-recall point, not a curve. However, machine learning models typically do not output discrete ...
Dave's user avatar
  • 296
3 votes

Upsampling vs downsampling. Which to use when?

You should use the one you need for your problem, when you know which components of your signal are of interest to you. Let's say you have in your electronic editing an ADC digitizing 40M samples per ...
Nathan Huchon's user avatar
3 votes

Audio classification without deep learning

From what you've mentioned it looks like the task is for environmental sound event detection. I think that the best starting point for you is to check the DCASE challenge (Detection and Classification ...
jojeck's user avatar
  • 11.1k
3 votes

How is this system nonlinear

This system may cause a hallucination because of its similarity to the algebraic equation $y = x + 1 $ which is a linear one indeed as stated in the wikipedia link to System_of_linear_equations ...
Fat32's user avatar
  • 28.3k
3 votes

How is this system nonlinear

A linear system means that the system's output should scale with the input, and the system's output should combine given two inputs. Look at the scaling property, you scale the input and this results ...
Engineer's user avatar
  • 3,042
2 votes

What are characteristics of shadows in an image given an outdoor setting from an image processing point of view?

The characteristics of the shadow are as follows: It is always dark regardless of the color of the object or the color of the light used to make a shadow It only shows a dark outline of the object It ...
amina saja's user avatar
2 votes
Accepted

Subgradient Method for K-Means Like Problem

I don't see why you would like to use subgradients for that. Correct me if I'm wrong, but when the problem is fully differentiable (kmeans actually is), the subgradient is the gradient vector $\nabla ...
Tolga Birdal's user avatar
  • 5,465
2 votes

Detecting automobile honking

if you wanted to make use of the fact that the horn is normally two horns at different pitches, you might consider a pair of tone detectors (using either BPF or parametric EQ or a Goertzel filter and ...
robert bristow-johnson's user avatar
2 votes
Accepted

Can we determine if a filter is butterworth or chebyshev from its physical topology?

As pointed out in a comment by Jason R, you can obviously come up with some random coefficients for the numerator and denominator polynomials of the filter's transfer function, and you'll end up with ...
Matt L.'s user avatar
  • 90.3k
2 votes
Accepted

Compute ADSR: How? Does it make sense?

... Instrument Recognition using pyAudioAnalysis. I was wondering if results could be improved by also analyzing the ADSR shape of the samples. In a pattern recognition setting, additional features ...
A_A's user avatar
  • 10.7k
2 votes

feature selection for classification for rare classes

Try one of Arizona State - Feature Selection Algorithms for feature selection: ...
Sofiane's user avatar
  • 178
2 votes

From MFCC to Machine learning. What are the steps?

There are two general things you can do with a machine learning algorithm: 1. Regression-- take input data and return an output numerical value. This is also known as curve-fitting, parameter ...
Robert L.'s user avatar
  • 2,222
2 votes

What would the target matrix to train Neural Network?

Example with the following numbers (I use random numbers): There are 6 possible classes (face expressions in your case). You have 2000 examples (lets say 2000 photos of faces from which you know the ...
pablo_worker's user avatar
2 votes

What is a segmentation mask in the paper "Fast Edge Detection Using Structured Forests"

This is a widely known paper (Fast Edge Detection Using Structured Forests). I will address the points you rasied: Patch vs. Label Size The patches are 32x32 yet ...
Royi's user avatar
  • 19.7k
2 votes

Python: Least Squares Support Vector Machine (LS-SVM)

There is a package called FukuML. In their description (Version 0.4.1) they write: Support Vector Machine Primal Hard Margin Support Vector Machine Binary Classification Learning Algorithm Dual ...
Royi's user avatar
  • 19.7k
2 votes

Identifying Instruments within a music file

Due to lack of reputation, I am unable to comment and am putting a response as an answer here. In general, this is an extremely difficult problem because of the wide variety of instruments and their ...
Ash's user avatar
  • 915
2 votes
Accepted

Classification of Signals using Features Extracted from Wavelet Scattering Coefficients

Expanding on my related answer but for wavelet scattering: Higher T -> greater time-shift invariance. Higher Q -> greater ...
OverLordGoldDragon's user avatar
2 votes
Accepted

Decision level fusion

In case there's no indication of a winner, you can just pick one at random - that can't be worse on average than just doing one model, if all three models are equally likely to be correct. You might ...
Marcus Müller's user avatar
2 votes

Log of Filterbank Energies

Why is this done? Mostly because human auditory perception works this way. The relationship between energy and perceived loudness is logarithmic. That is not only true for hearing but for most other ...
Hilmar's user avatar
  • 45.3k
2 votes
Accepted

Classification of a system

You’re correct, that’s not a causal system. You’re correct, that’s not a linear system. The additivity property doesn’t apply, but neither does the homogeneity. To see this, consider $$\alpha y[n] = \...
Jdip's user avatar
  • 6,265
1 vote

How to deal with audio with different length in Audio Classification

If the signals were of the same duration but obtained using different sampling rates, so that they have different sample lengths, you can resample the shorter sequence with a higher sampling rate to ...
Fat32's user avatar
  • 28.3k

Only top scored, non community-wiki answers of a minimum length are eligible