Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Related to the calculation, verification, usage, and requirements for Mel Frequency Cepstral Coefficients.

0
votes
0answers
7 views

MFCC Feature Reduction for Similarity Search

I'm working on creating song level features for music tracks. ...
0
votes
0answers
3 views

Praat Script for Speaking rate

I am using below code for speaking rate in Praat. vcd_frames = Count voiced frames tot_frames = Get number of frames vcd2tot_frames = vcd_frames / tot_frames Is that right?
0
votes
0answers
17 views

MFCC and DFT in signal processing [closed]

Can someone please briefly describe and if possible derive what are the MFCC coefficients of a signal? I've referred to this page here and there is a term called DCT. Can someone explain these two ...
1
vote
1answer
29 views

How does a telephone change your voice? [closed]

Is it due to vocal length normalization during MFCC? Please be kind enough to explain.
0
votes
1answer
11 views

MFCC window size at different sampling rates

The general recommendation for window size when calculating MFCC seems to be 20-40 msec. This is most often recommended in a context of 16000 samples per second, so leading to a window containing 320-...
0
votes
1answer
48 views

Given MFCC values for some wav’s, how can I easily tell if all speakers are the same?

Context: for a research project I have at regular times a batch of wav files with recordings of voice. The hypothesis is that all speakers in a batch are the same, but there might be 1 or a few “...
0
votes
0answers
24 views

issue with the MFCC and GMM for audio recognition

i am working on a project related to audio events recognition in real time like a door bell, baby crying, footstep, I have 9 categories of sound events so the first step i did was getting many wav ...
0
votes
0answers
28 views

issue in the mfcc function in java and matlab,not the same

I am working on a project for recognizing and identifying the sounds in real time(like baby crying, birds, door knocking...)by java, so I made a model by using audio files for 9 categories of sound by ...
0
votes
0answers
32 views

Why MFCC have varying length dimensions?

I have recently started to use MFCC as a feature for a project. However, I am unable to understand why MFCC have varying 2nd dimension size even when I chose the number of coefficients to be 40.
0
votes
0answers
10 views

How to calculate the time from the frame number in mfcc. would be helpful if any formula is suggested. fs=16000,overlap=10ms

Speech signal processing How to calculate the time from the frame number in mfcc. would be helpful if any formula is suggested. fs=16000,overlap=10ms
0
votes
0answers
15 views

Estimating a distribution of feature of sound based on a factor

I am currently working on creating a model of sound of inside of a car based on speed. To be specific, making a Gaussian distribution of MFCC(13 dim) for each speed, i.e. car running at 30 kmph, ...
0
votes
1answer
26 views

Speech Processing applications: stereo data for features

I am working on speech databases that have a stereo format. I want to extract spectral information (Mel-filterbanks, MFCC, LPCC) and also some other prosody features like the fundamental Frequency F0. ...
1
vote
2answers
46 views

Is there such thing as harmony independent timbre characteristic of a sound?

I was wondering if any of you know about any technique to extract a harmony (e.g. harmony in a shape of a chromagram) independent timbre characteristic of a sound frame. What I'm after is a version ...
0
votes
0answers
27 views

Derivative of a MFCC matrix

While reading this (see feature extraction section, subsection 4.1), I came across the following: The per-frame values for each coefficient are summarized across time using the following summary ...
1
vote
1answer
155 views

Machine Learning - any suggestions to solve Python rounding errors?

I am working with Python to isolate voiced segments from music using the Jamendo corpus for singing detection. Training a model, I break my audio into frames, and have a label (0,1) for each frame. ...
0
votes
0answers
68 views

Rookie Question regarding hop length and MFCC

Apologies for the basic question but I am a data scientist dipping my toes into the world of digital signal processing for the first time and have ran into an issue which is preventing me from running ...
0
votes
0answers
42 views

non-Mel Frequency Cepstral Coefficients

I'm trying to summarize the frequency domain information of an electrical signal as a feature engineering step for a machine learning algorithm. My hypothesis is that an anomaly will appear in the ...
0
votes
0answers
93 views

How to combine/append mfcc features with rmse and fft using librosa in python 2.7

I have an audio file say myfile.wav I trained a neural network based on fft features, and it is giving pretty good results for detecting particular classes of sounds. I want to expand above ...
0
votes
0answers
13 views

MFFC - Source moving towards the recorder in time

I'm doing my master thesis, it's about classifying ships using sonars. I'm using MFCC to extract the features. The question that I have is, since the ship will move towards the sonar in time, will I ...
0
votes
0answers
35 views

merge frame features matrix to one vector that describe the whole signal

I am trying to build a speaker identification system I use mfcc feature and lpcc feature first I split each sound into frames and compute mfcc and lpcc feature for each frame finally I have 379 frames ...
0
votes
1answer
115 views

The origin of constants in mel-scale formula

To convert frequency to mel, we usually use formula: $$\mathrm{mel}(f) = 1127 \ln \left(1 + \frac{f}{700}\right)$$ I wonder where are $1127$ and $700$ came from? I've read the paper which ...
0
votes
1answer
61 views

Mathematical reason for MCPP in audio recognition?

MCPP uses a weird graph of human phychoacoustics measurements called MEL scale to process digital audio. Why is MEL used in DSP voice recognition if it's based on logarithmic human perception, and ...
-1
votes
3answers
59 views

Features Used for Instrument Recognition?

I'm building a neural network for instrument recognition based on the IRMAS data set. However, I'm a bit at a loss for what features to use. MFCC seems to be quite popular but extracting this per ...
0
votes
0answers
79 views

number of FFT points

I have a framed and windowed signal at 320 samples. I was advised that I need to do n-point FFT of 512. But is that possible? What happens. Does it just pad the signal with zeros. I thought I read ...
0
votes
0answers
45 views

Piece Wise Function For Triangular Filter for MFCC

Below is the code I have been writing to try to create a mel triangular filter bank. I start with 300 to 8000 hz range, convert the frequency to mels, and then mels back into frequency to then get ...
-1
votes
1answer
69 views

Synchronizing 2 seperate speech audio signals

I have two speech signals: one with a man reading a passage, and one with a woman reading the same passage. I want to synchronize these signals so that, for each word, their readings line up. The ...
-1
votes
1answer
140 views

MFCC in Speech Recognition and ANN

I have a dataset with over 2000 examples of digits (0 to 9) recorded on wav files. I'm trying to process these files with MFCC so that later I could train an Artificial Neural Network (ANN). My ...
0
votes
1answer
59 views

Trouble understanding an article about MFCC

I'm willing to apply the same audio preparation that this article page 3. However, I don't understand the final part : ...
2
votes
2answers
394 views

Is it possible to apply a frequency filter a time domain signal?

Is it possible to frequency filter a time domain signal, without converting the signal to a frequency domain.. My question comes in regards how MFCC according to wiki and other pages describe the ...
0
votes
0answers
40 views

Why the $\tt filtbankm$ function returns $\tt 1+floor(n/2)$ samples?

I'm just trying to simulate the MFCC algorithm by different separated blocks in Simulink. so, for applying triangular Mel filters in to $\lvert \mathrm{FFT}\rvert^2$ , I've tried to use ...
2
votes
1answer
445 views

MFCC delta: How to compute delta, in real time, with no future frames?

I am trying to compute Delta coefficients for real-time audio analysis. As far as I know, a valid formula is: $$d_t= \frac{\displaystyle\sum_{n=1}^{N}n\left(c_{t+n}-c_{t-n}\right)}{2\displaystyle\...
1
vote
0answers
153 views

How to use frame based audio features for machine learning

I have an audio recording (wav file) that is 2 seconds long. That is my sample and it needs to be classified as [class_A] or [class_B]. To extract MFCC features, I divided the sample into frames (183 ...
0
votes
2answers
402 views

Using k Nearest Neighbour & Dynamic Time Warping for keyword spotting

As stated in the title, I am currently researching a method using k-NN, specifically, as either an alternative or as a supplement to the DTW algorithm in keyword spotting based on MFCC. I have read ...
0
votes
1answer
134 views

Signal Processing and Emotion Recognition

I have to write a paper on emotion recognition. More specifically on how different parameters affect the algorithms effectiveness. I have already read a lot about this and done research using ...
-1
votes
1answer
461 views

Applying dtw on mfcc

I have calculated 26 MFCCs for two sample speech data. My mfcc matrices thus contain 26 columns and 120 rows each, where 120 is the number of frames. Now I want to apply DTW on them and I am doing ...
4
votes
1answer
1k views

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

I'm studying speech-recognition, in particular the use of MFCC for feature extraction. All examples I've found online tend to graph a series of MFCC extracted from a particular utterance as follows (...
0
votes
1answer
68 views

What is the use of perception calculation in Speaker Identification?

I'm currently trying to find audio features to train a neural network that distinguishes people, and I came across MFCC which is used a lot for speech verification. As far as I understand the ...
1
vote
0answers
64 views

Can MFCC consist any zero values?

After extracting audio features using some library, I just realized that sometimes it (MFCC) might or might not have zero values. At what time/event does MFCC could have zero values? Because it's (...
-1
votes
2answers
263 views

Music recommendation by Cepstral coefficients

I have to make a music recommender system by taking signal features. I have decided to take MFCC coefficients as feature vector. So I extracted a dataset of 13 MFCC coefficients for each song. Here ...
0
votes
1answer
326 views

Comparing band-pass filters and convolutional kernels?

I am currently working on extracting features for speech recognition purposes. I wanted to try an approach similar to MFCC features in which the center frequency of each band pass filters are placed ...
0
votes
0answers
63 views

Is it possible to classify sounds from one long sound file?

I was successfully able to classify sounds by training and testing MFCC of separate sound files (a short file for each class). My question is whether I can classify sounds (e.g. vehicle engine sounds) ...
1
vote
2answers
1k views

How to apply a mel-filterbank to a signal?

I found this description. According to this, the next step is a "binning" where binning means that each FFT magnitude coefficient is multiplied by the corresponding filter gain and the results ...
3
votes
1answer
1k views

From MFCC to Machine learning. What are the steps?

I was able to get a dataset with MFCC coefficients. However, depending on the length of my sound file I get a different sized matrix. As in, 13 (13 MFCC coefficients) by XXX, where XXX will vary ...
0
votes
0answers
152 views

Clarification on generating a code book using vector quantization

In typical speech or speaker recognition programs, after extracting feature vectors from an audio signal, you are left with an MxN feature vectors, where M is the number of frames extracted from your ...
0
votes
1answer
398 views

Replicating Research: Feature Vectors of Audio Samples

I'm trying to make a few classifiers with scikitlearn. I'm using the Urban Sound database, and trying to replicated their research for a baseline. However, I don't understand how they derive their ...
1
vote
1answer
219 views

Applying a Liftering function to an audio signal

Is it necessary to perform the liftering function before applying MFCC to an audio signal?
2
votes
1answer
3k views

MFCC feature vector from wav file

I am trying to implement a spoken language identifier from audio files, using Neural Network. I need to generate one feature vector for each audio file. From what I have read the best features (for ...
1
vote
2answers
2k views

what is the mel scale?

I am not sure I understand what the Mel Scale is. Googling doesn't give me various answers. I seem to be getting the same response again and again. Which would be something like: "The mel scale ...
1
vote
2answers
469 views

Why is cepstrum used in MFCC instead of autocorrelation sequence?

I know that the inverse Fourier transform of the power spectral density $P(k)$ gives the autocorrelation sequence $A(n)$ (By Wiener-Khinchin theorem): $${\cal F}^{-1}\left\{P(k)\right\}=A(n)$$ And ...
1
vote
1answer
105 views

MFCC for very short signals

I have very short signals (usually 100 samples from a 44100 hz audio recording ). These are 'bang' noises that a hammer makes on a piece of metal. I want to use these short signals as input to some ...