Exponenta Banner

Segmentation

Detect and isolate speech and other sounds

Detect speech and other sounds and locate their start and end times. For streaming applications, use a voice activity detector (VAD) to output the probability that speech is present in a given frame. You can also use Speech-to-Text Transcription to create time-aligned word labels for speech signals.

Apps

Audio LabelerDefine and visualize ground-truth labels

Objects

voiceActivityDetectorDetect presence of speech in audio signal

Functions

detectSpeechDetect boundaries of speech in audio signal
classifySoundClassify sounds in audio signal

Blocks

Voice Activity DetectorDetect presence of speech in audio signal

Featured Examples

Cocktail Party Source Separation Using Deep Learning Networks

Cocktail Party Source Separation Using Deep Learning Networks

Isolate a speech signal using a deep learning network.

Open Live Script
Keyword Spotting in Noise Using MFCC and LSTM Networks

Keyword Spotting in Noise Using MFCC and LSTM Networks

Identify a keyword in noisy speech using a deep learning network. In particular, the example uses a Bidirectional Long Short-Term Memory (BiLSTM) network and mel frequency cepstral coefficients (MFCC).

Open Live Script
Voice Activity Detection in Noise Using Deep Learning

Voice Activity Detection in Noise Using Deep Learning

Detect regions of speech in a low signal-to-noise environment using deep learning. The example uses the Speech Commands Dataset to train a Bidirectional Long Short-Term Memory (BiLSTM) network to detect voice activity.

Open Live Script

Audio Toolbox Documentation

Support