Abstract
Automatic speech recognition, often incorrectly called voice recognition, is a computer based software technique that analyzes audio signals captured by a microphone and translates them into machine interpreted text. Speech processing is based on techniques that need local CPU or cloud computing with an Internet link. An activation word starts the uplink; “OK google”, “Alexa”, … and voice analysis is not usually suitable for autonomous limited CPU system (16 bits microcontroller) with low energy. To achieve this realization, this paper presents specific techniques and details an efficiency voice command method compatible with an embedded IOT low-power device.
Highlights
Human Machine interface based on speech recognition systems is a reality made possible through an Internet link and multi-threaded, multi-pipelined processor architecture or open source applications
This paper aims to analyze the development of a low cost and low power speech recognition system
The structure of the isolated word speech recognition system can be distinguished in two phases: The training phase—a user dictates the entire vocabulary used in the voice commands in order to create the reference audio signatures of the commands
Summary
Human Machine interface based on speech recognition systems is a reality made possible through an Internet link and multi-threaded, multi-pipelined processor architecture or open source applications. The main challenge in this project is to realize the speech recognition system on embedded hardware, using limited resources (computing power, embedded energy) and based on a very small microcontroller (16 bits). This is a difficult task taking into account that a speech recognition system requires high processing power for the audio signal treatment [1] [2]. The system is designed to be speaker independent, so it is capable in recognizing voice commands spoken by different persons. The goal of the system is to help people with disabilities in making their lives easier, by letting them control different things only with voice commands. These describe the state of art, the analytical description of the system, followed by the algorithm description, and the recognition technique to conclude with results of the recognition
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.