EdgeRNN: A Compact Speech Recognition Network With Spatio-Temporal Features for Edge Computing

Abstract

Driven by the vision of Internet of Things, some research efforts have already focused on designing a network of efficient speech recognition for the development of edge computing. Other researches (such as tpool2) do not make full use of spatial and temporal information in the acoustic features of speech. In this paper, we propose a compact speech recognition network with spatio-temporal features for edge computing, named EdgeRNN. Alternatively, EdgeRNN uses 1-Dimensional Convolutional Neural Network (1-D CNN) to process the overall spatial information of each frequency domain of the acoustic features. A Recurrent Neural Network (RNN) is used to process the temporal information of each frequency domain of the acoustic features. In addition, we propose a simplified attention mechanism to enhance the portion of the network that contributes to the final identification. The overall performance of EdgeRNN has been verified on speech emotion and keywords recognition. The IEMOCAP dataset is used in speech emotion recognition, and the unweighted average recall (UAR) reaches 63.98%. Speech keywords recognition uses Google's Speech Commands Datasets V1 with a weighted average recall (WAR) of 96.82%. Compared with the experimental results of the related efficient networks on Raspberry Pi 3B+, the accuracies of EdgeRNN have been improved on both of speech emotion and keywords recognition.

An Online Arrangement Method of Difficult Actions in Competitive Aerobics Based on Multimedia Technology

“…In the last three years, many methods are proposed to handle the online arrangement method of difficult actions; here, we introduced four outstanding methods proposed by Onan and Toçoglu (Eichner) [24], Yang et al [25], Zhang and Tao (Sapp) [26], and Hossain and Muhammad (MODEC) [27], which can be used to solve the related works In order to investigate the effectiveness of our proposal and other methods, here we take the F1-score into account to assess the experiment results, which can be defined as follows:…”

Finite Element Structure Analysis of Automobile Suspension Control Arm Based on Neural Network Control

“…In the last three years, many methods are proposed to handle the related problem; here, we introduced three outstanding methods, that is, APIT [23], DV-Hop [24], and CNNA [25], which can be used to solve the related works taking different kinds of network structures. APIT is a graphbased network that builds connections between different risk nodes.…”

Research on Basketball Goal Recognition Based on Image Processing and Improved Algorithm

“…In the last three years, many methods are proposed to handle the problem of basketball goal automation prediction; here we introduced three outstanding methods such as GNB [21], RNB [22], and CNB [23], which can be used to solve the related works taking different kinds of network structures. GNB is a graph-based network that builds connections between different risk nodes.…”