Mouse Movement using Speech and Non-Speech Characteristics of Human Voice

In the modern era, mouse control has become an important part of human computer interaction which is difficult for physically disabled people. This research paper presents a system called as Vocal Mouse (VM). This device will allow users to continuously control the mouse pointer using words as well as sounds by varying vocal parameters such as vowel quality, loudness and pitch. Traditional method of using only standard spoken words was inefficient for performing continuous tasks and they are often recognized poorly by automatic speech recognizers. Now, VM will allow users to work on both continuous and discrete motion control. This includes commands given as words or regular sounds consisting of vowels and consonants. Low-level acoustic features are extracted in real time using LPC (Linear Predictive Coding). Pattern recognition is performed using a new proposed technique called “minimum feature distance technique”. This proposed technique is based on calculating distances between the spoken word and each stored word in the library during training process. Features from pattern recognition module are processed to produce output in the form of cursor’s 2-D movement. VM can be used by novice users without extensive training and it presents a viable alternative to existing speech-based cursor control methods.