Design and realization of an intelligent access control system based on voice recognition

FPGA Design of Voice Enabled Ignition using G279 for Modal Based Speech Compression

“…This means that they can confirm who a person is and therefore assess their authorization levels. This technology, as stated by [2] is accurate with a 98% confidence interval, leading to a safe accurate and dependable system [3].…”

“…Talker recognition judges a voice that needs to be identified from several talker and talker confirmation judges whether or not a voice comes from a certain talker, having a yes or no output. Two important parameters of the system would be the capability for error identification and the rejection identification ratio [3]. These refer to the mistake made by the voice signal of non-users accepted by the system and the mistake made by the voice signal of users rejected by the system.…”

“…It can be divided into two broad categories of talker recognition and voice recognition [3]. Talker recognition can be further subdivided, such that they are either relevant to text, which builds speech parameters from a read text or not relevant to text which doesn't rule the pronunciation content of the speakers.…”

“…Modal based speech compression which has applications in voice activity detection and includes a linear predictive stage is required by [3]. In that implementation, the PAR-COR function was used to compute the linear prediction coefficients and perform the linear prediction analysis.…”

“…Software implementations such as [6] and [3] typically employ computationally difficult models as seen specifically in [access controls] inclusion of a software component to simplify the computational process. Hardware implementations utilize numerous memory models and parallel processing to perform specifically the digitization stage.…”