Google llc (20240347060). CONTEXTUAL SUPPRESSION OF ASSISTANT COMMAND(S) simplified abstract

CONTEXTUAL SUPPRESSION OF ASSISTANT COMMAND(S)

Organization Name

google llc

Inventor(s)

Victor Carbune of Zurich (CH)

Matthew Sharifi of Kilchberg (CH)

Ondrej Skopek of Zurich (CH)

Justin Lu of Zurich (CH)

Daniel Valcarce of Zurich (CH)

Kevin Kilgour of Oetwil an der Limmat (CH)

Mohamad Hassan Rom of Zurich (CH)

Nicolo D'ercole of Oberrieden (CH)

Michael Golikov of Merlischachen (CH)

CONTEXTUAL SUPPRESSION OF ASSISTANT COMMAND(S) - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240347060 titled 'CONTEXTUAL SUPPRESSION OF ASSISTANT COMMAND(S)

The patent application describes a process that uses warm word models to analyze a stream of audio data and identify specific words or phrases associated with an assistant command.

• The implementation involves using an automatic speech recognition (ASR) model to process the audio data, including a preamble and postamble, to determine if the user intended to give an assistant command.
• Additionally, a speaker identification (SID) model can be used to verify the user's identity and authorization to execute the command.
• The technology aims to improve the accuracy and efficiency of voice command systems by better understanding user intent and authorization.

Potential Applications: - Voice-controlled assistants - Smart home devices - Automotive infotainment systems

Problems Solved: - Enhancing user experience with voice commands - Improving security and authorization processes

Benefits: - Increased accuracy in recognizing user commands - Enhanced user privacy and security measures

Commercial Applications: Title: "Enhancing Voice Command Systems for Improved User Experience" This technology can be utilized in various industries such as consumer electronics, automotive, and home automation to provide more intuitive and secure voice command functionalities.

Questions about the technology: 1. How does the use of warm word models improve the accuracy of voice command recognition? 2. What are the potential privacy implications of using speaker identification technology in voice command systems?

Original Abstract Submitted

some implementations process, using warm word model(s), a stream of audio data to determine a portion of the audio data that corresponds to particular word(s) and/or phrase(s) (e.g., a warm word) associated with an assistant command, process, using an automatic speech recognition (asr) model, a preamble portion of the audio data (e.g., that precedes the warm word) and/or a postamble portion of the audio data (e.g., that follows the warm word) to generate asr output, and determine, based on processing the asr output, whether a user intended the assistant command to be performed. additional or alternative implementations can process the stream of audio data using a speaker identification (sid) model to determine whether the audio data is sufficient to identify the user that provided a spoken utterance captured in the stream of audio data, and determine if that user is authorized to cause performance of the assistant command.