Keyword spotting -- Detecting commands in speech using deep learning

2023/12/09 by Rai, Sumedha, Li, Tong, Lyu, Bella
#Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Human-Computer Interaction (cs.HC) #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2312.05640

Abstract

Speech recognition has become an important task in the development of machine learning and artificial intelligence. In this study, we explore the important task of keyword spotting using speech recognition machine learning and deep learning techniques. We implement feature engineering by converting raw waveforms to Mel Frequency Cepstral Coefficients (MFCCs), which we use as inputs to our models. We experiment with several different algorithms such as Hidden Markov Model with Gaussian Mixture, Convolutional Neural Networks and variants of Recurrent Neural Networks including Long Short-Term Memory and the Attention mechanism. In our experiments, RNN with BiLSTM and Attention achieves the best performance with an accuracy of 93.9 %

Related

• Deep Spoken Keyword Spotting: An Overview
• Speech Augmentation Based Unsupervised Learning for Keyword Spotting
• Multi-layer Attention Mechanism for Speech Keyword Recognition
• Attention-Free Keyword Spotting
• Online Keyword Spotting with a Character-Level Recurrent Neural Network