Small-footprint Keyword Spotting Research Articles

Speech densely connected convolutional networks for small-footprint keyword spotting

Speech densely connected convolutional networks for small-footprint keyword spotting

Joint Framework of Curriculum Learning and Knowledge Distillation for Noise-Robust and Small-Footprint Keyword Spotting

Joint Framework of Curriculum Learning and Knowledge Distillation for Noise-Robust and Small-Footprint Keyword Spotting

Feature reduction based transfer structural subspace learning for small-footprint cross-domain keyword spotting via linear discriminant analysis

Small-footprint keyword spotting has received considerable attention in recent years, which is often conducted on the assumption that the predefined keywords in training and testing data are obtained under the same condition. However, in practical situations, this assumption does not hold due to the widespread existence of various speech scenarios or voice-embedded devices. To tackle this problem, in this paper, we propose a new transfer subspace learning method called feature reduction based transfer structural subspace learning (FRTSSL) for small-footprint cross-domain keyword spotting. FRTSSL aims to learn a domain-invariant and discriminative subspace by which (1) feature reduction is used to high dimensional features to avoid unnecessary computation; and (2) transfer structural subspace learning jointly exploits the statistical properties and geometric structure to reduce the distribution discrepancy of the source and target domains based on a joint linear discriminant analysis (LDA) framework; and (3) the feedback term is constructed for improving the discrimination of the subspace based on source labels and pseudo-target labels. To preserve the intrinsic geometric structure of samples in the projection subspace, we first preserve the global subspace structure by imposing the reconstruction constraints on the reconstruction coefficient matrix, and then we preserve the space relationship of samples using a graph regularization method. Furthermore, we formulate a minimization problem that integrates marginal and conditional distribution alignment, reconstruction constraints, and graph regularization into the joint LDA framework, giving an effective optimization algorithm. Experimental results on four cross-domain keyword datasets show that our method outperforms some state-of-the-art conventional transfer learning methods and no transfer learning methods.

Small-Footprint Keyword Spotting for Controlling Smart Home Appliances Using TCN and CRNN Models

Smart homes feature automatic fire/smoke detection, voice-operated assets and appliances etc. More often, smart home appliances like lights, fans, etc., can be controlled through voice commands. Voice-operated devices like Alexa, Siri, and Google Assistant, are not new in the current age concerning voice command execution. However, working with these supports requires a global connection with the internet that costs time and bandwidth. Controlling home appliances need concise commands involving keywords on/off. Further, to operate the home appliances, bandwidth consumption for internet is not a wise idea. Through this paper, models based on Temporal Convolutional Networks (TCN) and Convolutional Recurrent Neural Networks (CRNN) have been studied for Keyword Spotting (KWS) by training models with keywords pronounced in different accents. The performance of these models is compared, and their ability to detect unknown words is studied. Finally, how these models are suitable for building Smart Home assistants to control home utilities with minimum bandwidth consumption is discussed.

Error-Diffusion Based Speech Feature Quantization for Small-Footprint Keyword Spotting

Error-Diffusion Based Speech Feature Quantization for Small-Footprint Keyword Spotting

Building and benchmarking an Arabic Speech Commands dataset for small-footprint keyword spotting

The introduction of the Google Speech Commands dataset accelerated research and resulted in a variety of new deep learning approaches that address keyword spotting tasks. The main contribution of this work is the building of an Arabic Speech Commands dataset, a counterpart to Google’s dataset. Our dataset consists of 12000 instances, collected from 30 contributors, and grouped into 40 keywords. We also report different experiments to benchmark this dataset using classical machine learning and deep learning approaches, the best of which is a Convolutional Neural Network with Mel-Frequency Cepstral Coefficients that achieved an accuracy of ∼98%. Additionally, we point out some key ideas to be considered in such tasks.

An End-to-End Model Based on Multiple Neural Networks with Data Augmentation for Keyword Spotting

In this paper, we propose a network for small footprint keyword spotting. It includes four parts, data augmentation, Time-Delay Neural Network (TDNN) and Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and attention mechanism. Data augmentation is Google SpecAugment with time warping and frequency mask and time mask to the spectrum on clean data set and noisy data set. TDNN and CNN model the spectrogram features from the time and space dimensions. RNN-type networks include RNN, Long Short-Term Memory network (LSTM), Gated Recurrent Unit (GRU), Bidirectional Long Short-Term Memory network (BiLSTM), and Bidirectional Gated Recurrent Unit (BiGRU). The RNN extracts hidden layer features and transforms them into high-level representations. The attention mechanism is selected to generate different weights and multiplied by the high-level representation generated by the RNN to obtain a fixed-length vector. Finally, we use a linear transformation and softmax function to generate scores. We also explored the size of attention mechanism, two attention mechanisms, rectified linear unit and hidden layer of RNN. Our model has achieved a true positive rate of 99.81% at a 5% false positive rate.