Speech Recognition

Speech command recognition, spoken digit recognition, keyword spotting

Speech recognition involves detecting and identifying speech, such as voice commands, in audio signals. Follow the examples to see workflows that apply feature extraction, machine learning, and deep learning to speech recognition applications.

Topics

AI for Speech Command Recognition

Build, train, compress, and deploy a deep learning model for speech command recognition.
- STEP 1: Train Deep Learning Network for Speech Command Recognition
- STEP 2: Prune and Quantize Speech Command Recognition Network
- STEP 3: Apply Speech Command Recognition Network in Simulink
- STEP 4: Apply Speech Command Recognition Network in Smart Speaker Simulink Model
- STEP 5: Deploy Smart Speaker Model on Raspberry Pi

Featured Examples

Speech Command Recognition Using Deep Learning

Use a pretrained deep learning model to perform speech command recognition on streaming audio.

Open Live Script

Spoken Digit Recognition with Wavelet Scattering and Deep Learning

Classify spoken digits using both machine and deep learning techniques. In the example, you perform classification using wavelet time scattering with a support vector machine (SVM) and with a long short-term memory (LSTM) network. You also apply Bayesian optimization to determine suitable hyperparameters to improve the accuracy of the LSTM network. In addition, the example illustrates an approach using a deep convolutional neural network (CNN) and mel-frequency spectrograms.

Open Live Script

Voice Activity Detection in Noise Using Deep Learning

Perform batch and streaming voice activity detection (VAD) in a low SNR environment using a pretrained deep learning model.

Open Live Script

Train Voice Activity Detection in Noise Model Using Deep Learning

Train a BiLSTM network to perform voice activity detection (VAD) in a low SNR environment.

Open Live Script

Speech Emotion Recognition

Implement a simple speech emotion recognition system using a BiLSTM network.

Open Live Script

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

Keyword Spotting in Simulink

Use a pretrained deep learning model in Simulink^® to identify a keyword in speech.

Open Live Script