Mel Spectrogram

Extract mel spectrogram from audio

Since R2022a

• 

Libraries:
Audio Toolbox / Features

Description

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.

Examples

Extract Mel Spectrogram

Extract a mel spectrogram using the Mel Spectrogram block.

• Open Model

Ports

Input

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.

Data Types: single | double

Output

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.

Data Types: single | double

fvec — Center frequencies

row vector

Center frequencies of the bandpass filters in Hz, returned as a row vector with number of elements equal to the number of bands.

Dependencies

To enable this port, select the Output frequency vector parameter.

Data Types: single | double

Parameters

Filter Bank Parameters

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) | off

When you select this parameter, the block sets the Frequency range to [0,fs/2], where fs is the sample rate. The sample rate is determined by the Inherit sample rate from input and Input sample rate (Hz) parameters.

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.

Dependencies

To enable this parameter, clear the Auto-determine frequency range parameter.

Filter bank design domain — Domain to design filter bank

linear (default) | warped

Domain in which the block designs the filter bank, specified as linear or warped. Set the filter bank design domain to linear 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) | area | none

Normalization technique used for the filter bank weights, specified as bandwidth, area, or none.

• 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.

Mel style — Mel style

oshaughnessy (default) | slaney

Style of the mel scale, specified as oshaughnessy or slaney.

Visualize filter bank — Open plot to visualize filter bank

button

Open plot to visualize the filters in the frequency domain.

Output frequency vector — Specify additional output port for center frequencies

off (default) | on

When you select this parameter, the block displays an additional output port, fvec. This port outputs the center frequencies of the bandpass filters.

Spectrogram Parameters

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) | off

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, windowLength)

Overlap length of adjacent analysis windows, specified as an integer in the range [0, windowLength), where windowLength is the length of the analysis window, which is specified by Window.

Auto-determine FFT length — Automatically determine FFT length

on (default) | off

When you select this parameter, the block automatically sets the FFT length to the window length, numel(Window).

FFT length — Number of DFT points

1024 (default) | positive integer

Number of points used to calculate the DFT, specified as a positive integer.

Dependencies

To enable this parameter, clear the Auto-determine FFT length parameter.

Spectrum type — Type of spectrum

magnitude (default) | power

Type of spectrum, specified as magnitude or power.

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)

Apply logarithm — Apply logarithm

off (default) | on

When you select this parameter, the block applies a base 10 logarithm to the spectrogram.

Simulation Parameters

Inherit sample rate from input — Specify source of input sample rate

off (default) | on

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.

Dependencies

To enable this parameter, clear the Inherit sample rate from input parameter.

Block Characteristics

Data Types	double | single
Direct Feedthrough	no
Multidimensional Signals	no
Variable-Size Signals	no
Zero-Crossing Detection	no

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using Simulink® Coder™.

The Mel Spectrogram block supports optimized code generation using single instruction, multiple data (SIMD) instructions. For more information about SIMD code generation, see Generate SIMD Code from Simulink Blocks for Intel Platforms (Simulink Coder).

Version History

Introduced in R2022a

R2024a: Apply logarithm to spectrogram

Select the Apply logarithm parameter to apply a base 10 logarithm to the spectrogram.

R2023b: Support for Slaney-style mel scale

Set the Mel style parameter to slaney to use the Slaney-style mel scale.

R2023a: Generate optimized C/C++ code for computing mel spectrogram

The Mel Spectrogram block supports optimized C/C++ code generation using single instruction, multiple data (SIMD) instructions.