Get Started with 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.

Tutorials

Analyze Signals

Use Signal Analyzer App
Visualize, measure, analyze, and compare signals in the time, frequency, and time-frequency domains.

Preprocess Signals

Align Signals with Different Start Times
Synchronize data collected by different sensors at different instants.
Compute Envelope Spectrum of Vibration Signal
Compute the envelope spectrum of a signal and combine app-generated scripts and functions into a single workflow.

Find Patterns and Extract Features

Find Peaks in Data
Locate the local maxima in a set of data and determine if those peaks occur periodically.

Design, Analyze, and Apply Digital Filters

Practical Introduction to Digital Filter Design
Use the designfilt function to design FIR and IIR filters based on frequency response specifications.
Practical Introduction to Digital Filtering
Design, analyze, and apply digital filters to remove unwanted content from a signal without distorting the data.

Perform Spectral and Time-Frequency Analysis

Practical Introduction to Frequency-Domain Analysis
Perform and interpret basic frequency-domain signal analysis using simulated and real data.
Practical Introduction to Time-Frequency Analysis
Perform and interpret basic time-frequency signal analysis of nonstationary signals.

Apply Signal Processing to AI

Classify ECG Signals Using Long Short-Term Memory Networks
Classify heartbeat electrocardiogram data using deep learning and signal processing.
Waveform Segmentation Using Deep Learning
Segment human electrocardiogram signals using time-frequency analysis and deep learning.

Featured Examples

Extract Voices from Music Signal

Use Signal Analyzer to extract voices from a song by duplicating and filtering signals.

Open Live Script

Process a Signal with Missing Samples

Signals often have missing samples. To provide estimates for these values, use resampling.

Open Live Script

Find and Track Ridges Using Reassigned Spectrogram

Use the reassigned spectrogram in Signal Analyzer to sharpen the time and frequency localization of spectrograms.

Open Live Script

Label Signal Attributes, Regions of Interest, and Points

Use Signal Labeler to label attributes, regions, and points of interest in a set of whale songs.

Open Live Script

Automate Signal Labeling with Custom Functions

Use Signal Labeler to locate and label QRS complexes and R peaks of ECG signals.

Open Live Script

Take Derivatives of a Signal

Use a differentiator filter to differentiate a signal without amplifying the noise.

Open Live Script

Interactive Learning

Signal Processing Onramp
This free, two-hour tutorial provides an interactive introduction to practical signal processing methods for spectral analysis.

Videos

What Is Signal Processing Toolbox?
Perform signal processing, signal analysis, and algorithm development using Signal Processing Toolbox.

Signal Processing and Machine Learning Techniques for Sensor Data Analytics
This video presents a classification system able to identify the physical activity of a human subject based on smartphone-generated accelerometer signals.

Signal Analysis Made Easy with the Signal Analyzer App
Learn to perform signal analysis tasks in MATLAB with the Signal Analyzer app.

Introduction to Signal Processing Apps in MATLAB
Use Signal Analyzer to import, visualize, preprocess, and analyze an electrocardiogram signal.

Understanding the Discrete Fourier Transform and the FFT
The discrete Fourier transform (DFT) transforms discrete time-domain signals into the frequency domain. The most efficient way to compute the DFT is using a fast Fourier transform (FFT) algorithm. This tech talk answers a few common questions that are often asked about the DFT and the FFT. It covers an overview of the algorithm where you’ll be walked through an understanding of why you might look at the absolute value of the FFT, how bin width is calculated, and what the difference is between one-sided and two-sided FFTs.

Understanding Power Spectral Density and the Power Spectrum
Learn how to get meaningful information from a fast Fourier transform (FFT). There is a lot of confusion on how to scale an FFT in a way that provides an understanding of the properties of the time-domain signal, which is addressed in this tech talk. Specifically, it covers how to go from an FFT to amplitude, power, and power density and why you may choose one representation over another – and the scenarios in which they are valid.