Abstract
The consistent increase in the number and ownership population of mobile devices introduces a variety of limitations. A set of this limitations revolve around interactivity. The overly dependent haptic mechanism of interaction has caused device falls, slower time to interaction, health concerns, and limited support for the disabled among other problems. There is need to formulate innovative techniques that facilitate our interaction with these devices for users. In order to achieve this, a Real-time Voice Recognition Algorithm is formulated that lets users of mobile devices acquire freedom to move about and reduce the need for constantly glancing at their screen. This is achieved by allowing users to verbally command their devices to carry out ordinary tasks. An added unique feature is that it also offers offline access as any commands given by a user are processed and executed locally on the device.
Highlights
The Smart phone market is a standout among the most focused markets on the planet today with different contenders, for example, Samsung, Apple, Asus, Google, Sony, Microsoft, and Research in Motion among others being secured a tight race to keep up or develop in the top position
This paper describes the development of an efficient speech recognition system using different techniques such as Mel Frequency Cepstrum Coefficients (MFCC), Vector Quantization (VQ) and Hidden Markov Model (HMM)
We describe large vocabulary Continuous Speech Recognition (LVCSR) system SPOJUS++ which has been developed in our laboratory for over 20 years and recently fully reimplemented from scratch
Summary
One of the problems faced in speech recognition is that the spoken word can be vastly altered by accents, dialects and mannerisms. Wax, and developed the “Ediphone” to compete directly with Columbia The purpose of these products was to record dictation of notes and letters for a secretary (likely in a large pool that offered the service as shown in Figure 1) who would later type them out (offline), thereby circumventing the need for costly stenographers. Proper location of regions of speech reduces the amount of processing The objective of this Project is the development of “Speech recognition based system to control electrical appliances” and the analysis techniques that would provide sharply improved speech recognition accuracy in any type of noisy environments. The above systems rely on the clarity of the captured speech but many of the real-world environments include noise and others that mitigate the system performance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
