Inventions on using sound and speech in GUI

The personal computers are often equipped with a sound card that is capable of audio processing. This enables GUI applications to use sounds and synthesized speech, such as warning messages, voice alerts and guides to the user. Most sound cards also take input from a microphone, which are often used to pickup user voice and digitize them through audio processing circuitry. Voice recognition system Voice recognition facilitates a human interaction with the machine. VR may be used to replace the manual task of pushing buttons on a wireless telephone keypad. This is useful when the hands of the user are busy with other activities like driving a car. Voice recognition enables the user to enter information into the computer by speaking that information. For example, the voice recognition software can be used to enter text into a word processor program instead of typing the text on a keyboard. Normally the voice recognition system needs to be trained before it can function optimally. The system should learn the speech patterns of a particular user. The digitized audio signals are stored with their text equivalents and compared with the voice being spoken. In specific situations the voice recognition (VR) device should be capable of continuous speech recognition (CSR) to recognize a continuous speech, such as, speaking/ recognizing a telephone number or email address, which are generally spoken without a pause. ⇛ The computer users may like to use VRS when their hands are busy. For example, a person can enter text through dictation while driving a car. ⇛ Voice enabled systems are useful for users having poor or partial vision. The voice commands supplement to the visual commands. ⇛ The VRS can be effectively used in maintaining phone books, address books etc. The user can dial telephones just by calling a telephone number or a name. ⇛ Sound is used in various applications to inform " alert " , " error " or " ok " conditions. ⇛ The multimedia applications and gaming applications often use voice messages to say " sorry " , " that's right " , " thank you " etc. to make the session more interactive and attractive. ⇛ The VRS requires lot of training and customization to be effectively used by individual users as each individual falls into different voice patterns. ⇛ The voice interface is complex and error prone. Calling a telephone number does not give …