Stack Overflow
Stack Overflow

Questions tagged [mfcc]

Mel-Frequency Cepstral Coefficients. The name given to an alternate representation of speech signals based on its frequency content. Very popular way to represent a speech signal as a feature vector. Used primarily for speech recognition tasks.

Mel Frequency Cepstral Coefficients (MFCC) are coefficients obtained when a speech signal is analysed by a series of filter banks with logarithmically spaced center frequencies on the Mel-scale. This choice of center frequencies is significant because it mimics the human ear. MFCC are computed from the magnitude mel-spectrogram by log-scaling, and applying the Discrete Cosine Transform to compute the cepstrum. MFCC is very popular for speech recognition tasks.

312 questions
0
votes
1 answer

Cepstrum pitch detection

I want to get pitch values using MFCC features in matlab using a function from this link: [F0, T, C] = spPitchTrackCepstrum(y, 20000, 25.6, 10, 'hamming', 0); But all numbers are positive (without unvoiced values). Please, help me figure out how to…
Viktoriya Ivanova
  • 23
  • 5
0
votes
0 answers

Error at the time of testing system using htk

I have trained the system, but at the time of testing the system I am getting the following error:- **ERROR [+6310] OpenParmChannel: cannot open Parm File Path/T_TUPT_M0002_PN_10012_1.mfc ERROR [+6313] OpenAsChannel: OpenParmChannel failed ERROR…
user77
  • 41
  • 1
  • 10
0
votes
1 answer

MFCC in speech recognition

I spent whole last week to search on MFCC and related issues. Now I can get MFCC features from a .wav file in a 2-dimensional vector, coff[56][12], let's say. 12 is the number of coefficents I want to extract and 56 is the number of…
duong_dajgja
  • 4,196
  • 1
  • 38
  • 65
0
votes
1 answer

MFC: Adding fade-in , fade-out effect to polygon region

I Want To Fade-in, Fade-out a particular region created by me. but when i use animatewindow() It fades out entire window which is not visible earlier when i created polygon region. how do i do this? help can be appreciated.
user2059287
  • 15
  • 1
  • 8
0
votes
1 answer

The formula of computing the Mel-filterbank coefficient

I am working with MFCC in a project about Speech Recognition. According to the document in this website http://practicalcryptography.com/miscellaneous/machine-learning/guide-mel-frequency-cepstral-coefficients-mfccs/, the formula of computing the…
user2530847
  • 49
  • 2
  • 12
0
votes
3 answers

MATLAB mfcc gmdistribution fit for Speech Recognition Program

I'm new to Matlab and doing a signal processing project(Speech Recognition). After doing some calculations, I get some values known as MFCC (Mel-Frequency Cepstral Coefficient) in a matrix. I'm now supposed to apply a Gaussian Mixture Model (GMM)…
Shark
  • 165
  • 1
  • 10
0
votes
1 answer

Dealing with outlier in a MFFC with DTW setup

I have a small command recognition system in which the user first records his commands then later the system tries to recognize them . The front end's feature vector are MFCC's coefficients. The back end does recognition using DTW to align these…
Ray
  • 339
  • 3
  • 12
0
votes
0 answers

Can CoMIRVA package be used in android?

I am planning to extract MFCC features in real time so that it can be used for speech recognition in my android application. For the same I have found that there is a package available in java called CoMIRVA. I tried using the package for my…
user1957734
  • 1
  • 1
  • 4
0
votes
1 answer

my likelihood value resulted from gmm is correct?

I'm making a program emotion-recognition in speech. Using a mfcc + K-mean + GMM, I got a likelihood like -15012, -43400, -8000 It was so bigger value than I though. Is it right value? Wave file's length usually 2~3 and I init using below…
joejo
  • 111
  • 11
-1
votes
1 answer

2D array Classification using Python

I am trying to build a voice recognition application. Until now, I already extract the mfcc feature from 10 sample voice. Each sample yield different shape like shown below: (698, 12) (414, 12) (610, 12) (586, 12) (698, 12) (282, 12) (250, 12) (370,…
chandra sutrisno
  • 491
  • 4
  • 17
-1
votes
1 answer

how many channels in a CNN for sound classification?

I am a beginner with Tensorflow and machine learning in general.For my project I have to classify urban sound data. I have extracted mfccs of my sample data and now I want to classify them by using a CNN in Tensorflow. I don't know how many…
Emanuela Liaci
  • 165
  • 1
  • 12
-1
votes
1 answer

how to apply DTW on 2 dimensional feature vector matrix obtained from mfcc?

I have two 2 dimensional feature vector obtained from MFCC. How can I apply Dynamic Time Warping(DTW) on it? Can I find the similarties between two vector in percentage?
Sushant Gurung
  • 1
1 2 3
…
20
21