Pretrained Models

Transfer learning, sound classification, feature embeddings, pretrained audio deep learning networks

Audio Toolbox™ provides MATLAB^® and Simulink^® support for pretrained audio deep learning networks. Locate and classify sounds with YAMNet and estimate pitch with CREPE. Extract VGGish or OpenL3 feature embeddings to input to machine learning and deep learning systems. Use i-vector systems to produce compact representations of audio signals for applications such as speaker recognition, verification, identification, and diarization. Use detectspeechnn to perform voice activity detection (VAD).

Using pretrained deep learning networks requires Deep Learning Toolbox™. The Audio Toolbox pretrained networks are available in Deep Network Designer (Deep Learning Toolbox).

Functions

expand all

VGGish

`vggishEmbeddings`	Extract VGGish feature embeddings
`vggish`	VGGish neural network
`vggishPreprocess`	Preprocess audio for VGGish feature extraction

YAMNet

`classifySound`	Classify sounds in audio signal
`yamnet`	YAMNet neural network
`yamnetGraph`	Graph of YAMNet AudioSet ontology
`yamnetPreprocess`	Preprocess audio for YAMNet classification

OpenL3

`openl3Embeddings`	Extract OpenL3 feature embeddings
`openl3`	OpenL3 neural network
`openl3Preprocess`	Preprocess audio for OpenL3 feature extraction

CREPE

`pitchnn`	Estimate pitch with deep learning neural network
`crepe`	CREPE neural network
`crepePreprocess`	Preprocess audio for CREPE deep learning network
`crepePostprocess`	Postprocess output of CREPE deep learning network

i-Vectors

`speakerRecognition`	Pretrained speaker recognition system
`ivectorSystem`	Create i-vector system

VAD

`detectspeechnn`	Detect boundaries of speech in audio signal using AI
`vadnet`	Voice activity detection (VAD) neural network
`vadnetPreprocess`	Preprocess audio for voice activity detection (VAD) network
`vadnetPostprocess`	Postprocess frame-based VAD probabilities

Blocks

expand all

VGGish

VGGish Embeddings	Extract VGGish embeddings
VGGish Preprocess	Preprocess audio for VGGish feature extraction
VGGish	VGGish embeddings extraction network

YAMNet

Sound Classifier	Classify sounds in audio signal
YAMNet	YAMNet sound classification network
YAMNet Preprocess	Preprocess audio for YAMNet classification

OpenL3

OpenL3 Embeddings	Extract OpenL3 embeddings
OpenL3 Preprocess	Preprocess audio for OpenL3 embeddings extraction
OpenL3	OpenL3 embeddings extraction network

CREPE

Deep Pitch Estimator	Estimate pitch with CREPE deep learning neural network
CREPE	CREPE deep pitch estimation neural network
CREPE Preprocess	Preprocess audio for CREPE deep pitch estimation
CREPE Postprocess	Postprocess output of CREPE pitch estimation network

Apps

Deep Network Designer

Design, visualize, and train deep learning networks

Topics

Audio Transfer Learning Using Experiment Manager
Configure an experiment that compares the performance of multiple pretrained networks applied to a speech command recognition task using transfer learning.
Classify Human Voice Using YAMNet on Android Device (Simulink Support Package for Android Devices)
This example shows how to use the Simulink® Support Package for Android™ Devices and a pretrained YAMNet network to classify human voices.

Related Information

Featured Examples

Transfer Learning with Pretrained Audio Networks in Deep Network Designer

Interactively fine-tune a pretrained network to classify new audio signals using Deep Network Designer.

Open Live Script

Investigate Audio Classifications Using Deep Learning Interpretability Techniques

Use interpretability techniques to investigate the predictions of a deep neural network trained to classify audio data.

Open Live Script