Hot answers tagged

23 votes
Accepted

Cepstral Mean Normalization

Just to make things clear - this property is not fundamental but important. It is the fundamental difference when it comes to using DCT instead of DFT for spectrum calculation. Why do we do Cepstral ...
  • 10.7k
11 votes
Accepted

What's the correct graphical interpretation of a series of MFCC vectors?

The way MFCC's are always used is by feeding them into the classifier. This can be done on a frame-by-frame basis (12x1 vector), or by concatenating (...
  • 10.7k
7 votes

Mel filter in MFCC - is it necessary?

Mel filter bank is important due to following reasons: It applies the Mel-frequency scaling, which is perceptual scale that helps to simulate the way human ear works. It corresponds to better ...
  • 10.7k
6 votes
Accepted

MFCC - Significance of number of features

Number of filter banks One of the last steps in the MFCC's calculation is measuring the energy in the filter banks. We do that because want to reduce the dimensionality of our input vector (amplitude ...
  • 10.7k
5 votes
Accepted

What is the advantage of applying a Hamming window for MFCC calculations?

Ideally you would only see that frequency as a narrow peak but because of the finite-length window you also get that other artificial crud: Windowing equals time domain multiplication by the window ...
5 votes

what is the mel scale?

To stand on @hotpaw2's answers, think of Mel as one kind of pyscho-acoustic scale, derived from a set of experiments on human subjects, others are Bark & ERB Why have such a scale? Imagine a ...
  • 1,730
5 votes
Accepted

Applying a Liftering function to an audio signal

No, liftering is never applied before computing MFCC because liftering is defined as a windowing operation in the cepstral domain. So you need cepstral coefficients in order to be able to apply ...
  • 81k
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 ...
4 votes
Accepted

Sinusoidal liftering in implementations of MFCC

This paper$^1$ suggests: that the reason is because the filtered versions give less weight to the higher coefficients which provide less discrimination than the lower ones. That paper references ...
  • 23.1k
4 votes

Two voice pronunciation comparison similarity MFCC + DTW

I will answer your questions in reverse order. 4: DTW (Dynamic Time Warping) is not a library but an algorithm. It allows aligning two sequences by warping them in time. You can use it for pretty ...
  • 10.7k
3 votes
Accepted

Framing an audio signal

The MFCC summary you link seems to leave out the typical windowing function applied before each FFT. Segmenting longer data into shorter finite length FFT inputs does an implicit rectangular ...
  • 34.1k
3 votes
Accepted

Determine the time length of audio training samples?

It's a very bad idea to stack together consecutive frames in a single vector. By doing so, you are training a classifier to recognize the exact same sound as the one in your training database, ...
  • 19.1k
3 votes
Accepted

Why are MFCCs of two equivalent signals completely different?

You say: I stream this file via VLC-Player and Icecast2-Server, receive it in Java (with the Player of Javazoom-Lib) When you receive the stream in Java, what is the stream format? You say ...
  • 1,730
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 ...
  • 151
3 votes
Accepted

MFCC extraction last step DCT or IDCT

I don't believe there is a right answer. DCT or IDCT will achieve the same purpose: decorrelating to put most energy in fewer coefficients. Whatever you do next with your MFCC (compression, feature ...
  • 206
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!
  • 1,730
3 votes
Accepted

How to apply a mel-filterbank to a signal?

Binning is an averaging operation on the (squared) magnitudes of the DFT. You would maybe have $256$ DFT bins but only around $20$ outputs of the filter bank. So you need to average groups of DFT bins ...
  • 81k
3 votes
Accepted

filterbank: understand the different responses at the center frequency of each filter

Normalizing the filterbanks by their widths is optional and totally up to you (similarly to the warping scale Mel/Bark). Depending on your application, you can start without normalization and see what ...
  • 10.7k
2 votes
Accepted

How to organize MFCC features?

Natural order would be to save it on frame by frame basis - that's the way you calculate them, otherwise you would need some gymnastics to do so. What's more, each 12 coefficients will be one vector ...
  • 10.7k
2 votes
Accepted

MFCCs and chord recognition

MFCC's are related strictly to spectrum shape and what's more - these are relaying on the mel scale. Additionally each coefficient is a DCT value from fitted cosinusoids to log-energies. Thus ...
  • 10.7k
2 votes

Speech recognition using mfcc and neural network

Usually your training data and your test data are different, otherwise your results will be unrealistically good. However, for a first test of your implementation, you can simply use your training ...
  • 81k
2 votes

Vowel detection using MFCC

You may just implements a VAD (voice activity detector) whose parameters are high enough to filter out voiced consonants. One VAD which always amazed me is the zero crossing rate, because it is so ...
2 votes
Accepted

Speech recognition using MFCC and DTW(Dynamic Time Warping)?

At the very beginning let me warn you that DTW approach is suitable only for spoken word recognition. Nonetheless it is interesting as a basic exercise. I assume that you have a database of training ...
  • 10.7k
2 votes

Why discrete cosine transform may not maintain locality

In a frequency-like transformation (Fourier, discrete cosine, Walsh), one generally ends up with a sequence of coefficients that account for each frequency component over the support of the basis ...
2 votes

Why discrete cosine transform may not maintain locality

First you have a misconception in your question which I suggest you to edit first: The paper https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/TASLP2339736-proof.pdf is not authored ...
2 votes

How to match a piece of very short audio based on key and pitch to find a piece in a large database that is most similar to it?

well, the "sound" of something depends on a lot of different parameters, which are not all well understood, nor all innumerated. could be loudness contour. brightness contour. pitch contour. degree ...
2 votes

Why is cepstrum used in MFCC instead of autocorrelation sequence?

Usually in speech signal processing cepstrum is used to represent low and high frequency components , which are multiplied with each other(in time domain its a slowly varying signal convolved with ...
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 ...
  • 2,172
2 votes
Accepted

What is the use of perception calculation in Speaker Identification?

Well, I don't know whether it'll actually help you – you just said it would! Now, in any case, using an algorithm to extract features from a signal that mimics or resembles human perception should ...
2 votes
Accepted

Applying dtw on mfcc

Let's unpack this code: 1 mfcc1=mfcc1'; 2 mfcc2=mfcc2'; 3 M=simmx(mfcc1,mfcc2); 4 [p,q,c]=dp(1-M); 5 v=c(size(c,1),size(c,2)) in line 3, ...
  • 1,730

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