Questions tagged [mfcc]

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

64 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
5 votes
0 answers
1k views

Zero-padding of MFCC coefficients

I am trying to implement speech recognition using backpropagation algorithm, and I have been following this paper. I have followed it all the way, except that it tells me to zero-pad the coefficients ...
motiur's user avatar
  • 414
5 votes
1 answer
400 views

how to handle different durations of audio data?

I am new to signal preprocessing, I read about mel_spectrograms, MFCC's. Now I want to apply it and use the CNN model, But the data which I have for practice is having audio of different durations, ...
Ravi Teja's user avatar
4 votes
0 answers
3k views

Verifying MFCC Final Result

I have created a Octave code for MFCC calculation for speech recognition, which takes a wav file as input and then gives the MFCC as the output. But the final results are a bit confusing, so I am ...
Mohit's user avatar
  • 173
3 votes
0 answers
58 views

Supervised instrument recognition

Is it possible to use NMF for a sort of supervised polyphonic instrument recognition? I have training data for a timpani and training data for a bongo (or a bongo, snare and box drum). How can I ...
Andrew B.'s user avatar
3 votes
0 answers
14k views

MFCC calculation

I've got a project and need to calculate MFCCs. I tried to read some tutorials and then make a MATLAB function but I seem to have wrong answers. I'd like to feed MFCCs to one of the classification ...
Celdor's user avatar
  • 452
3 votes
0 answers
631 views

Questions about Bark scale filter bank implementation for bfcc's

I have a few questions regarding the implementation of Bark scale filter banks for the calculation of bark frequency cepstral coefficients. 1) Which filter shape is most commonly used and why? ...
melinnde's user avatar
  • 155
3 votes
0 answers
459 views

Finding similar fragment in recorded speech

I use MFCC algorithm for calculation of Mel-frequency coefficient for 2 files and DTW algorithm with Euclidean distance for finding similarity. I have results values around 400-600 on the files with ...
Vbif's user avatar
  • 131
2 votes
1 answer
81 views

What are some speech features that vary with what the speaker says?

I have been working on a text-dependent speaker verification project. I have used mel-frequency cepstrum coefficients(MFCC) for the project. As far as I know, MFCC coefficients depend on the vocal ...
Wanderer's user avatar
2 votes
0 answers
22 views

Text dependent speaker verification using MFCC and vector quantization

I am trying to implement a text dependent speaker verification system. Here each speaker will speak their unique identification number and they will be granted access. I am trying to implement this ...
Wanderer's user avatar
2 votes
0 answers
82 views

Combining signals in MFCC space

I'm looking at a data augmentation method for training up a neural network of speech data. Currently I have two version of augmentation. The first method works by taking an audio file and mixing in a ...
Goz's user avatar
  • 475
2 votes
0 answers
177 views

How to calculate MFCCs over a narrow frequency range?

I have a bunch of brief (~1 second each) wave files, some of which contain a frequency-modulated sound of interest between about 3900-4500 Hz. I thought I might run MFCC calculations on these sound ...
m0ckingbird's user avatar
2 votes
0 answers
279 views

MFCC help: Same sound, different coefficients?

Problem: I'm getting totally different MFCC coefficients for identical and near identical sounds like several finger snaps or several desk taps. What am I missing? I thought since the timbre doesn't ...
Andrew B.'s user avatar
2 votes
0 answers
309 views

Most efficient algorithm for comparing two paths

I'm working with a Continuous Hidden Markov Model, and using the Viterbi Decoder which finds the best possible path for a given sequence. Here is how my algorithm works: ...
Phorce's user avatar
  • 485
2 votes
1 answer
787 views

How to compare 2 MFCC (compare them if they where created from same speaker)

There are multiple speakers. Each speaker generates multiple MFCC. If I'm getting two different MFCC, can we know if those MFCC came from 2 different speakers or same speaker ? How can we compare ...
Boom's user avatar
  • 121
1 vote
0 answers
48 views

MFCCs are useful for speech & music analysis. For music, why isn't the 12-tone scale used instead of the mel scale?

As far as I understand, the mel scale was developed empirically using something akin to "just noticeable differences" in a subject's perception of frequencies. The scale ends up being a log ...
sguis's user avatar
  • 11
1 vote
0 answers
10 views

Chunk a voice and do not save it in each step of processing

I need a way that when I get voice and chunk it with librosa Library when I do this my voice change to Typeless type . And I can not do any thing or do any progress in my voice . Other wise I don't ...
Mohammadhossein bagheri's user avatar
1 vote
0 answers
62 views

Why filter-bank energies coefficients are same through the frame?

I am trying to implement MFCC's from scratch in C++. In each frame, I am processing real-valued data to construct MFCC vectors. Although I think that my implementation is correct, the testing result ...
Yalçın Cenik's user avatar
1 vote
0 answers
314 views

Use the mean and standard deviation after MFCC extraction

I've noticed in some literature that the authors chose to use the mean and standard deviation of the extracted MFCC features. "ANALYSIS AND VOICE RECOGNITION IN INDONESIAN LANGUAGE USING MFCC ...
Joe's user avatar
  • 113
1 vote
0 answers
169 views

Is Discrete cosine transform Translational Invariant

I am using 2D Mellin-Cepstrum to extract features, If I use log-polar transform to get rotational invariance, the rotation is transformed to translation. Can I use DCT next to get translational ...
Radhika's user avatar
  • 11
1 vote
0 answers
46 views

Get Spectrogram from Filtered Power Spectrum

My objective is to get the higher resolution of spectrogram on the high-frequency area (2000 Hz - 5000 Hz) for a section of speech audio. I know that we typically apply Mel-scaled filter bank to get ...
John's user avatar
  • 11
1 vote
0 answers
90 views

Logarithmic Amplitude Spectral Subtraction

I'm diving into audio processing and I'm trying to wrap my head around spectral subtraction. I learned there are different approaches do it based on power, magnitude, oversubtraction. My task is to ...
lima0's user avatar
  • 9
1 vote
0 answers
14 views

Sound feature extraction too brief in comparison with manual annotation of sound. How to combine them?

Sound characteristics (features) are taken per e.g. 20 ms, but manual annotation takes place in durations of seconds. If we want to use these characteristics along with labels, how can this be ...
Andrew Pap's user avatar
1 vote
0 answers
262 views

Understanding MFCC

I am not from electrical or electronic background so my knowledge will be lacking. MFCC is represented by 39 values for each window frame. 12 values are the mel filter-bank and we get 13th value by ...
Naveen Gabriel's user avatar
1 vote
0 answers
43 views

Alone MFCC can identify difference between sound?

I am doing a project to identify different drum beats. There are lots of features like MFCC, Chroma Values, Spectral Bandwidth, Spectral Centroid, Zero Crossing Rate, etc. But most of the projects are ...
Asiri Amal's user avatar
1 vote
0 answers
1k views

How to overcome different MFCC coefficients distributions from different speech datasets?

I am using MFCC values as features for a machine learning model of speech, detecting age from a voice recording of a person. I work with voice datasets I found on the web: common-voice and vctk. ...
Shiran's user avatar
  • 11
1 vote
0 answers
265 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 ...
Learthgz's user avatar
  • 132
1 vote
0 answers
166 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 (...
muhrifqii's user avatar
1 vote
0 answers
2k views

What does the output of Gaussian Mixture Model (GMM) represents in a HMM-GMM based speech recognition application?

Till now I know that- first the speech is converted frames and feature vectors are calculated for each frame using MFCC. And while training the Acoustic model- HMM model is generate for each phoneme ...
user2530619's user avatar
1 vote
0 answers
856 views

Dealing with MFCC Feature Vectors of different sizes

I am working on a project where I am classifying coughs of a patient as either positive or negative for a certain pulmonary illness. What I have at the moment is multiple cough events, segmented ...
Renier Botha's user avatar
1 vote
0 answers
187 views

Implementation of DCT for MFCC

I am in the process of implementing MFCC and I'm unsure about the DCT part. This is how I implemented it (using DCT II). ...
nevos's user avatar
  • 161
1 vote
0 answers
3k views

Compare two voices and outline their similarity

I am trying to develop an application which records the voice of someone through a microphone. I will have a preset recorded voices for the same words. I then need to compare the real time recorded ...
mario.borg's user avatar
1 vote
0 answers
165 views

Features for speaker recognition

I'm trying to create my own program for speaker identification (text-independent) and have used MFCC features for that. But result of recognition is very poor. My supervisor told me that using MFCC ...
kobra's user avatar
  • 111
1 vote
0 answers
242 views

Extract Word Information From MFCC

I am making a pronunciation Scoring system, and I need to know how to separate the pronunciation information of an MFCC of a given spoken word, so that later i can match this MFCC with the MFCC of ...
Bassel Safwat's user avatar
1 vote
1 answer
513 views

How to average MFCCs from different speakers saying the same word?

I am trying to create a simple recognition system. i have recordings of several speakers saying the same word, let's say "west". I compute the MFCC feature vectors of word "west" from each speaker. If ...
ordineri's user avatar
1 vote
1 answer
860 views

Principal Component Analysis as a step between STFT and MFCC

For computing Mel Frequency Cepstral Coefficients you can use already calculated STFTs as a basis and perform the Mel frequency mapping on it. My question: Does it make a significant difference if I ...
Jamona's user avatar
  • 51
0 votes
0 answers
25 views

Musical Instrument Characterization

I am doing an undergraduate project where I want to first characterize an instrument based on its pitch and timbre and make an instrument recognition system afterward. Pitch characterization is pretty ...
Flash's user avatar
  • 1
0 votes
0 answers
39 views

Separating 'heart sound' from 'lung sound'

I have audio files recorded from electronic stethoscope and in those files I want to filter out heart sounds and retain just the breathing sounds. How can I do this using just the signal processing ...
hamza nawaz's user avatar
0 votes
0 answers
30 views

Isn't the MFCC feature good for real time applications?

I am interested in the audio classification problem. You can think of the problem as ML, but my question is from a signal processing perspective. I am questioning the classification performance of ...
Yalçın Cenik's user avatar
0 votes
0 answers
18 views

Use DFT twice for MFCC extraction engine or use both DFT and DCT?

I'm in the process of designing an MFC extraction engine on an FPGA using Verilog. My primary concern is whether I can implement the DFT twice in the MFCC calculation process: once before applying the ...
ALS's user avatar
  • 1
0 votes
0 answers
43 views

Preprocessing lung sound data: replication of paper method

I'm really new to signal processing research. I'm trying to replicate Kirill Kochetov and Andrey Filchenkov. 2021. Generative Adversarial Networks for Respiratory Sound Augmentation. In Proceedings ...
Asmaul Husna Shampa's user avatar
0 votes
0 answers
200 views

difference in speed between tensorflow implementations of mfcc and stft

I am trying to preprocess audio clips for a keyword spotting task that uses machine learning models. The first step is to calculate the spectrogram starting from the waveform and in order to do so I ...
Giacomo Zema's user avatar
0 votes
0 answers
36 views

How is 76 frames calculated mfcc for 1 sec signal with 25 msec window and 10 msec overlap?

I was studying about keyword detection and while doing some reading, I read we take 1 sec audio signal. We then divide it into 25msec sub sections with and overlap of 10msec. We apply mel filter bank ...
t0mkaka's user avatar
0 votes
0 answers
45 views

What acoustics do MFCCs correspond to?

My question is, what frequency ranges do MFCCs correspond to? My line of thinking thus far is that if your highest frequency in the signal was 8000 Hz, you could convert to Mels (= 2834 Mels), take 13 ...
Lisa's user avatar
  • 131
0 votes
0 answers
388 views

How do I interpret these mfcc graphs?

The first graph represents mfcc plot for female and the second for male. How do I interpret this graph with colors. and what is that color scale on the right? How do I differentiate gender from these ...
chaitra srikanth's user avatar
0 votes
0 answers
1k views

Understanding liftering as the final step in MFCCs features extraction

In the book here, they apply liftering, as a final step of MFCCs features extraction, to isolate the system component by multiplying the whole cepstrum by a rectangular window centred on lower ...
Abdulkader's user avatar
0 votes
0 answers
150 views

Why do we use the term "cepstral" in MFCCs, and how does it related to the cepstral domain?

As I know, we can get the cepstrum by taking the Inverse Discrete Fourier Transform (IDFT) of the log of the power spectrum. And we can get the Mel-frequency cepstral coefficients (MFCCs) by taking ...
Abdulkader's user avatar
0 votes
0 answers
19 views

What features capture the semantics of a sentence from a gien audio?

I have been thinking lately and looking up on what could be the possible features that capture the semantics of an audio and came across MFCC: MFCC features represent phonemes (distinct units of sound)...
Aruna Maurya's user avatar
0 votes
0 answers
208 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 ...
KamelK's user avatar
  • 21
0 votes
0 answers
314 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 ...
KamelK's user avatar
  • 21
0 votes
0 answers
599 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.
user5722540's user avatar