Extract mel spectrogram from audio
Audio Toolbox / Features
The Mel Spectrogram block extracts the mel spectrogram from the audio input signal. A mel spectrogram contains an estimate of the short-term, time-localized frequency content of the input signal in the mel frequency scale.
Port_1 — Audio input
column vector | matrix
Audio input signal, specified as a column vector or a matrix. When you specify a matrix, the block treats columns as independent audio channels.
spec — Mel spectrogram
matrix | 3-D array
Mel spectrogram, returned as a matrix or 3-D array. The dimensions of spec are L-by-M-by-N, where:
L is the number of spectra, which is determined by the Number of spectra parameter.
M is the number of bands, which is determined by the Number of bands parameter.
N is the number of channels in the input audio signal.
Trailing singleton dimensions are removed from the output.
This port is unnamed until you select the Output center frequencies parameter.
fvec — Center frequencies
Center frequencies of the bandpass filters in Hz, returned as a row vector with number of elements equal to the number of bands.
To enable this port, select the Output frequency vector parameter.
Number of bands — Number of bandpass filters
32 (default) | positive integer
Number of bandpass filters, specified as a positive integer.
Auto-determine frequency range — Automatically determine frequency range
on (default) |
When you select this parameter, the block sets the Frequency range
fs is the sample
rate. The sample rate is determined by the Inherit sample rate
from input and Input sample rate (Hz)
Frequency range (Hz) — Frequency range over which to design auditory filter bank
[0,22050] (default) | two-element row vector
Frequency range in Hz over which to design the auditory filter bank, specified as a two-element row vector.
To enable this parameter, clear the Auto-determine frequency range parameter.
Filter bank design domain — Domain to design filter bank
linear (default) |
Domain in which the block designs the filter bank, specified as
Set the filter bank design domain to
design the bandpass filters in the linear (Hz) domain. Set the filter bank
design domain to
warped to design the bandpass
filters in the warped (mel) domain.
Filter bank normalization — Normalization technique for filter bank
bandwidth (default) |
Normalization technique used for the filter bank weights, specified as
bandwidth–– Normalize the weights of each bandpass filter by the corresponding bandwidth of the filter.
area–– Normalize the weights of each bandpass filter by the corresponding area of the bandpass filter.
none–– The block does not normalize the weights of the filters.
Visualize filter bank — Open plot to visualize filter bank
Open plot to visualize the filters in the frequency domain.
Output frequency vector — Specify additional output port for center frequencies
off (default) |
When you select this parameter, the block displays an additional output port, fvec. This port outputs the center frequencies of the bandpass filters.
Window — Analysis window
hamming(1024,'periodic') (default) | real vector
Analysis window applied in the time domain, specified as a real vector.
Normalize window — Normalize analysis window
on (default) |
When you select this parameter, the block applies window normalization.
Overlap length — Overlap length of adjacent analysis windows
512 (default) | integer in the range [0,
Overlap length of adjacent analysis windows, specified as an integer in
the range [0,
windowLength is the length of the analysis window,
which is specified by Window.
Auto-determine FFT length — Automatically determine FFT length
on (default) |
When you select this parameter, the block automatically sets the FFT
length to the window length,
FFT length — Number of DFT points
1024 (default) | positive integer
Number of points used to calculate the DFT, specified as a positive integer.
To enable this parameter, clear the Auto-determine FFT length parameter.
Spectrum type — Type of spectrum
magnitude (default) |
Type of spectrum, specified as
Number of spectra — Number of spectra
1 (default) | positive integer
Number of spectra in the spectrogram, specified as a positive integer.
Number of spectra overlap — Number of overlapped spectra
0 (default) | integer in the range [0, Number of spectra).
Number of spectra overlapped across consecutive spectrograms, specified as an integer in the range [0, Number of spectra)
Inherit sample rate from input — Specify source of input sample rate
off (default) |
When you select this parameter, the block inherits its sample rate from the input signal. When you clear this parameter, you specify the sample rate in the Input sample rate (Hz) parameter.
Input sample rate (Hz) — Sample rate of input
44.1e3 (default) | positive scalar
Input sample rate in Hz, specified as a real positive scalar.
To enable this parameter, clear the Inherit sample rate from input parameter.