18750663. CONTEXTUAL SUPPRESSION OF ASSISTANT COMMAND(S) simplified abstract (GOOGLE LLC)

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 18750663 titled 'CONTEXTUAL SUPPRESSION OF ASSISTANT COMMAND(S)

The patent application describes a method for processing a stream of audio data to identify specific words or phrases associated with an assistant command, using warm word models and automatic speech recognition (ASR) models.

• Utilizes warm word models to identify specific words or phrases in audio data related to assistant commands.
• Processes preamble and postamble portions of the audio data using ASR models to determine user intent for the assistant command.
• Incorporates speaker identification models to verify user identity and authorization for the assistant command.

Potential Applications: - Voice-controlled assistants - Hands-free command systems - Speech recognition technology

Problems Solved: - Improving accuracy in identifying user commands - Enhancing user experience with voice-activated devices

Benefits: - Streamlined voice command processing - Increased security through user verification - Enhanced functionality of voice-controlled systems

Commercial Applications: Title: "Enhanced Voice Command Technology for Smart Devices" This technology can be applied in smart speakers, smartphones, and other IoT devices to improve user interaction and device control.

Questions about Voice Command Technology: 1. How does this technology improve user experience with voice-activated devices?

  This technology enhances user experience by accurately identifying user commands and improving the overall functionality of voice-controlled systems.

2. What are the potential security implications of using speaker identification models in voice command technology?

  Speaker identification models can enhance security by verifying user identity and authorization for specific commands, reducing the risk of unauthorized access to devices.

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.