Implementation of a Speech Recognition System in a DSC

Abstract

This paper describes the development and validation of an Embedded IsolatedWord Recognition System (IWR) for the Argentinian Spanish language, implemented on the STM32F4-Discovery platform. Its front-end extracts Mel Frequency Cepstral Coefficients (MFCC), while its classification step is based on the Dynamic Time Warping (DTW) algorithm. Since the system was conceived as a base platform for the research and development of speechbased command and control applications, it was designed to be modular and to meet real-time performance. The system includes a Real Time Operating System (RTOS) to manage various processing and control tasks, which can be easily reconfigured with different acquisition, processing and recognition parameters using a single file. The validation was done using a scenario of robotic control, achieving performance rates which demonstrates the practical usefulness of the system.

An INS/WiFi Indoor Localization System Based on the Weighted Least Squares

“…DTW has been applied to temporal sequences of video [ 29 ], audio [ 30 ], and graphics data [ 31 ]. One well-known application is automatic speech recognition, which copes with different speaking speeds [ 32 ]. In the indoor positioning system, DTW is often used to calculate the distance between two one-dimensional signals [ 33 , 34 ].…”

Embedded Real-time Operating System in Remote Viewing of Electrical Automation Equipment

“…A single file can be used to easily reconfigure different acquisition, processing and identification parameters. The verification is done using the robot control scenario, and the performance that proves the actual usefulness of the system is achieved [4].Perez Tijero H proposed a real-time platform for multi-processor and partitioned systems, which also considered communication requirements, It also describes the adaptation of MaRTE OS (a single-processor real-time operating system) to the XtratuM hypervisor of the multi-processor Intel x86 architecture [5].Wang J has developed a low-cost cloud sensor computing node with embedded Linux operating system, mobile agent middleware and open database functions. The information sharing and exchange is to use mobile agents to distribute analysis algorithms to cloud-aware computing nodes, process data locally and share analysis results [6].Ji Q proposes a fast and accurate real-time video detection and tracking algorithm suitable for embedded systems.…”