18421189. MULTI-MODAL INPUT ON AN ELECTRONIC DEVICE simplified abstract (Google LLC)

MULTI-MODAL INPUT ON AN ELECTRONIC DEVICE

Organization Name

Google LLC

Inventor(s)

Brandon M. Ballinger of San Franciso CA (US)

Johan Schalkwyk of Scarsdale NY (US)

Michael H. Cohen of Portola Valley CA (US)

William J. Byrne of Davis CA (US)

Gudmundur Hafsteinsson of Los Gatos CA (US)

Michael J. Lebeau of New York NY (US)

MULTI-MODAL INPUT ON AN ELECTRONIC DEVICE - A simplified explanation of the abstract

This abstract first appeared for US patent application 18421189 titled 'MULTI-MODAL INPUT ON AN ELECTRONIC DEVICE

Simplified Explanation

The computer-implemented input method editor process described in the abstract involves receiving spoken input from a user, converting it to text, and providing it as input to an application.

• User requests an application-independent input method editor with written and spoken input capabilities.
• User provides spoken input to the input method editor.
• Spoken input is converted to text.
• Text representing the spoken input is provided as input to the application.

Potential Applications

The technology described in this patent application could be applied in various fields such as:

• Speech-to-text applications
• Virtual assistants
• Language translation tools

Problems Solved

This technology addresses the following issues:

• Facilitating spoken input for users who prefer not to type
• Improving accessibility for individuals with disabilities
• Enhancing user experience by offering multiple input options

Benefits

The benefits of this technology include:

• Increased efficiency in inputting text
• Enhanced user convenience
• Improved accuracy in converting spoken input to text

Potential Commercial Applications

A potential commercial application for this technology could be in:

• Mobile devices
• Smart home devices
• Customer service chatbots

Possible Prior Art

One example of prior art in this field is the use of speech recognition software in virtual assistants like Siri and Alexa.

How does this technology handle different languages and accents?

This article does not address the specific methods used to handle various languages and accents in the speech-to-text conversion process.

What is the accuracy rate of the speech-to-text conversion?

The accuracy rate of the speech-to-text conversion is not mentioned in this article.

Original Abstract Submitted

A computer-implemented input-method editor process includes receiving a request from a user for an application-independent input method editor having written and spoken input capabilities, identifying that the user is about to provide spoken input to the application-independent input method editor, and receiving a spoken input from the user. The spoken input corresponds to input to an application and is converted to text that represents the spoken input. The text is provided as input to the application.