My Research

My tentative objective is to improve human speech recognition using a better system for extracting information to make the voice a more reliable method for security purposes, such to use the voice for opening doors or activate devices. To achieve this goal I will try to improve the processing of information extraction of the human voice using a better algorithm that can extract only the voice fragments by removing ambient noise as much as possible.

The human voice is a interesting topic, because it’s the way in what most of humans communicate, it is a protocol of communication between humans, but what will happened if we use this “protocol” to communicate with machines and electronic devices, will be wonderful that they can understand us and recognize the specific voice of each different person. Currently the algorithms human speech recognition are not 100% reliable, since they have the capacity to determine with certainty whether the speaker is who they say they are trying to use your voice in security systems. According to Robert M. Gray of Stanford University, the first ideas leading to LPC started in 1966 when S. Saito and F. Itakura of NTT described an approach to automatic phoneme discrimination that involved the first maximum likelihood approach to speech coding1. Then in 1999, Ericsson, one of Sweden's largest companies, is a provider of telecommunication and data communication systems develop a new voice recognition system for their T series mobile phones, this system use voice commands to set the agenda and 20 more customizable commands as answer, hang up and redial, this system was not so precise, sometimes you have to repeat several times the voice commands. The use of an better system for extracting information of human speech can have a lot of applications in the quotidian life of all people, like to open doors and windows or control devices more efficiently, if we can trust in the speech algorithm, we can even use it in security systems, I’m sure that it’s possible to improve the process of the human voice, we have the technology to the development of this project, to control a device with the voice can became like an extension of a hand, you will not need to move your arm or your fingers to activate and operate a device and it can have a lot of applications, for people who can’t move their body, they will be available turn on the television or the lights, even we can think in drive a car with the voice.