Signal Processing Toolbox

Perform signal processing and analysis

Signal Processing Toolbox provides functions and apps to manage, analyze, preprocess, and extract features from uniformly and nonuniformly sampled signals. The toolbox includes tools for filter design and analysis, resampling, smoothing, detrending, and power spectrum estimation. You can use the Signal Analyzer app for visualizing and processing signals simultaneously in time, frequency, and time-frequency domains. With the Filter Designer app you can design and analyze FIR and IIR digital filters. Both apps generate MATLAB scripts to reproduce or automate your work.

Using toolbox functions, you can prepare signal datasets for AI model training by engineering features that reduce dimensionality and improve the quality of signals. You can access and process collections of files and large datasets using signal datastores. With the Signal Labeler app, you can annotate signal attributes, regions, and points of interest to create labeled signal sets. The toolbox supports GPU acceleration in addition to C/C++ and CUDA^® code generation for desktop prototyping and embedded system deployment.

What Is Signal Processing Toolbox?

Signals plotted in time and time-frequency domains with corresponding labels within the Signal Labeler app.

Machine Learning and Deep Learning for Signals

Perform preprocessing, feature engineering, signal labeling, and dataset generation for machine learning and deep learning workflows. Use the Signal Labeler app to create ground truth datasets and extract features to train AI models.

Labeling Signals for AI Tasks with Signal Labeler App (3:33)

Documentation | Examples

Signals plotted in time, frequency, and time-frequency domains in the Signal Analyzer app.

Signal Exploration and Preprocessing

Visualize, preprocess, and explore signals using the Signal Analyzer app. Denoise, smooth, and detrend signals to prepare them for further analysis.

Signal Analysis Made Easy with the Signal Analyzer App (4:28)

Documentation | Examples

Time domain signals plotted in the Signal Labeler app with features extracted and displayed.

Feature Extraction and Signal Measurements

Measure and extract distinctive features in signals including peaks, power, bandwidth, distortion, and signal statistics. Compute metrics related to pulses and transitions. Extract features for an entire dataset using the Signal Labeler app.

Peak Analysis (4:27)

Documentation | Examples

Live editor task used to design a range of filters including lowpass, highpass, and bandpass filters.

Filter Design and Analysis

Design, analyze, and implement digital and analog filters. Use the Filter Designer app or the Design Filter live editor task to design a variety of digital FIR and IIR filters, such as lowpass, highpass, and bandstop.

Digital Filtering (4:48)

Documentation | Examples

Power spectral density plot showing 3dB bandwidth of two signals.

Spectral Analysis

Characterize the frequency content of a signal using spectral estimation and subspace techniques. Design, visualize, and implement windowing functions.

Documentation | Examples

STFT plotted as a waterfall plot of a voltage-controlled oscillator output, controlled by a sinusoid sampled at 10 kHz.

Time-Frequency Analysis

Visualize and compare time-frequency content of nonstationary signals using methods such as spectrogram, synchrosqueezing, and reassignment.

Documentation | Examples

Waterfall plot of an order-RPM map with gear and pinion graphics next to the plot.

Vibration Analysis

Characterize vibrations in mechanical systems. Use order analysis to analyze and visualize spectral content occurring in rotating machinery. Perform experimental modal analysis and fatigue analysis.

Documentation | Examples

Workflow of C code generation from MATLAB to generated code to processor hardware.

Code Acceleration and Generation

Accelerate the execution of your signal processing algorithms using a Graphics Processing Unit (GPU). Generate portable C/C++ source code, standalone executables, or standalone applications from your MATLAB code.

Documentation | Examples