Audio Processing

Design an autoencoder neural network to perform anomaly detection for machine sounds using unsupervised learning.

Perform speech enhancement using a pretrained filter and sum network (FaSNet) with ambisonic data.

Perform 3-D sound event localization and detection using a pretrained deep learning model.

Develop an x-vector system to perform speaker recognition.

Speaker diarization is the process of partitioning an audio signal into segments according to speaker identity. It answers the question "who spoke when" without prior knowledge of the speakers and, depending on the application, without prior knowledge of the number of speakers.

Train a deep learning model that detects the presence of speech commands in audio. The example uses the Speech Commands Dataset [1] to train a convolutional neural network to recognize a set of commands.

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).

Denoise speech signals using deep learning networks. The example compares two types of networks applied to the same task: fully connected, and convolutional.

Train and use a generative adversarial network (GAN) to generate sounds.

In this example, you perform batch and streaming voice activity detection (VAD) in a low SNR environment using a pretrained deep learning model. For details about the model and how it was trained, see Train Voice Activity Detection in Noise Using Deep Learning.

Illustrates a simple speech emotion recognition (SER) system using a BiLSTM network. You begin by downloading the data set and then testing the trained network on individual files. The network was trained on a small German-language database [1].

Create a multi-model late fusion system for acoustic scene recognition. The example trains a convolutional neural network (CNN) using mel spectrograms and an ensemble classifier using wavelet scattering. The example uses the TUT dataset for training and evaluation [1].

Use an end-to-end deep learning network for speaker-independent speech separation.

Develop a deep learning model to detect faults in an air compressor and package the system to operate on streaming data.

Perform audio event classification on Raspberry Pi^® using the YAMNet pretrained deep neural network from the TensorFlow™ Lite library.

Demonstrates code generation for keyword spotting using a Bidirectional Long Short-Term Memory (BiLSTM) network and mel frequency cepstral coefficient (MFCC) feature extraction on Raspberry Pi™. MATLAB® Coder™ with Deep Learning Support enables the generation of a standalone executable (.elf) file on Raspberry Pi. Communication between MATLAB® (.mlx) file and the generated executable file occurs over asynchronous User Datagram Protocol (UDP). The incoming speech signal is displayed using a timescope. A mask is shown as a blue rectangle surrounding spotted instances of the keyword, YES. For more details on MFCC feature extraction and deep learning network training, visit Keyword Spotting in Noise Using MFCC and LSTM Networks.

Deploy feature extraction and a convolutional neural network (CNN) for speech command recognition on Intel® processors. To generate the feature extraction and network code, you use MATLAB® Coder™ and the Intel® Math Kernel Library for Deep Neural Networks (MKL-DNN). In this example, the generated code is a MATLAB executable (MEX) function, which is called by a MATLAB script that displays the predicted speech command along with the time domain signal and auditory spectrogram. For details about audio preprocessing and network training, see Speech Command Recognition Using Deep Learning.

Generate a MATLAB^® standalone executable for acoustics-based machine fault recognition.

Deploy feature extraction and a convolutional neural network for speech command recognition on Raspberry Pi.