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 given set of commands.

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.

Deploy feature extraction and a convolutional neural network (CNN) for speech command recognition to Raspberry Pi™. To generate the feature extraction and network code, you use MATLAB Coder, MATLAB Support Package for Raspberry Pi Hardware, and the ARM® Compute Library. In this example, the generated code is an executable on your Raspberry Pi, which is called by a MATLAB script that displays the predicted speech command along with the signal and auditory spectrogram. Interaction between the MATLAB script and the executable on your Raspberry Pi is handled using the user datagram protocol (UDP). For details about audio preprocessing and network training, see Speech Command Recognition Using Deep Learning.

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.

Isolate a speech signal using a deep learning network.

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

Demonstrates a machine learning approach to identify people based on features extracted from recorded speech. The features used to train the classifier are the pitch of the voiced segments of the speech and the mel frequency cepstrum coefficients (MFCC). This is a closed-set speaker identification: the audio of the speaker under test is compared against all the available speaker models (a finite set) and the closest match is returned.

Speaker verification, or authentication, is the task of confirming that the identity of a speaker is who they purport to be. Speaker verification has been an active research area for many years. An early performance breakthrough was to use a Gaussian mixture model and universal background model (GMM-UBM) [1] on acoustic features (usually mfcc). For an example, see Speaker Verification Using Gaussian Mixture Models. One of the main difficulties of GMM-UBM systems involves intersession variability. Joint factor analysis (JFA) was proposed to compensate for this variability by separately modeling inter-speaker variability and channel or session variability [2] [3]. However, [4] discovered that channel factors in the JFA also contained information about the speakers, and proposed combining the channel and speaker spaces into a total variability space. Intersession variability was then compensated for by using backend procedures, such as linear discriminant analysis (LDA) and within-class covariance normalization (WCCN), followed by a scoring, such as the cosine similarity score. [5] proposed replacing the cosine similarity scoring with a probabilistic LDA (PLDA) model. [11] and [12] proposed a method to Gaussianize the i-vectors and therefore make Gaussian assumptions in the PLDA, referred to as G-PLDA or simplified PLDA. While i-vectors were originally proposed for speaker verification, they have been applied to many problems, like language recognition, speaker diarization, emotion recognition, age estimation, and anti-spoofing [10]. Recently, deep learning techniques have been proposed to replace i-vectors with d-vectors or x-vectors [8] [6].

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