20240021207. MULTI-FACTOR AUDIO WATERMARKING simplified abstract (GOOGLE LLC)

From WikiPatents
Jump to navigation Jump to search

MULTI-FACTOR AUDIO WATERMARKING

Organization Name

GOOGLE LLC

Inventor(s)

Aleks Kracun of New York NY (US)

Matthew Sharifi of Kilchberg (CH)

MULTI-FACTOR AUDIO WATERMARKING - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240021207 titled 'MULTI-FACTOR AUDIO WATERMARKING

Simplified Explanation

The patent application describes techniques for multi-factor audio watermarking. The method includes the following steps:

  • Receiving audio data.
  • Processing the audio data to generate predicted output that indicates the probability of one or more hotwords being present in the audio data.
  • Determining if the predicted output satisfies a threshold indicating the presence of the hotwords.
  • If the threshold is satisfied, processing the audio data using automatic speech recognition to generate a speech transcription feature.
  • Detecting a watermark embedded in the audio data.
  • If the watermark is detected, determining if the speech transcription feature corresponds to one of a plurality of stored speech transcription features.
  • If the speech transcription feature corresponds to one of the stored features, suppressing processing of a query included in the audio data.

Potential applications of this technology:

  • Content protection: The audio watermarking technique can be used to protect copyrighted audio content from unauthorized use or distribution.
  • Voice assistant security: The method can enhance the security of voice assistants by detecting and suppressing queries that may contain malicious intent or unauthorized commands.
  • Audio authentication: The watermarking technique can be used to verify the authenticity of audio recordings, ensuring they have not been tampered with or altered.

Problems solved by this technology:

  • Unauthorized use of copyrighted audio content can be prevented or detected.
  • Malicious or unauthorized commands given to voice assistants can be identified and suppressed.
  • Audio recordings can be authenticated and verified for their integrity.

Benefits of this technology:

  • Enhanced content protection and copyright enforcement.
  • Improved security and privacy in voice assistant systems.
  • Reliable authentication and verification of audio recordings.


Original Abstract Submitted

techniques are described herein for multi-factor audio watermarking. a method includes: receiving audio data; processing the audio data to generate predicted output that indicates a probability of one or more hotwords being present in the audio data; determining that the predicted output satisfies a threshold that is indicative of the one or more hotwords being present in the audio data; in response to determining that the predicted output satisfies the threshold, processing the audio data using automatic speech recognition to generate a speech transcription feature; detecting a watermark that is embedded in the audio data; and in response to detecting the watermark: determining that the speech transcription feature corresponds to one of a plurality of stored speech transcription features; and in response to determining that the speech transcription feature corresponds to one of the plurality of stored speech transcription features, suppressing processing of a query included in the audio data.

Retrieved from "http://wikipatents.org/index.php?title=20240021207._MULTI-FACTOR_AUDIO_WATERMARKING_simplified_abstract_(GOOGLE_LLC)&oldid=28237"