20240040035. DETECTION OF UNWANTED CALLS OR CALLER INTENT BASED ON A FUSION OF ACOUSTIC AND TEXTUAL ANALYSIS OF CALLS simplified abstract (RealNetworks LLC)

From WikiPatents
Jump to navigation Jump to search

DETECTION OF UNWANTED CALLS OR CALLER INTENT BASED ON A FUSION OF ACOUSTIC AND TEXTUAL ANALYSIS OF CALLS

Organization Name

RealNetworks LLC

Inventor(s)

Branimir Dropuljic of Zagreb (HR)

Michael J. Bordash of Newtown CT (US)

DETECTION OF UNWANTED CALLS OR CALLER INTENT BASED ON A FUSION OF ACOUSTIC AND TEXTUAL ANALYSIS OF CALLS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240040035 titled 'DETECTION OF UNWANTED CALLS OR CALLER INTENT BASED ON A FUSION OF ACOUSTIC AND TEXTUAL ANALYSIS OF CALLS

Simplified Explanation

The patent application describes a system and method for processing calls to determine if they are potentially fraudulent or unwanted. Here is a simplified explanation of the abstract:

  • The system extracts a speech signal from an audio signal associated with a call.
  • It identifies audio characteristics by analyzing the audio signal.
  • It generates a textual transcript of the audio signal using automatic speech recognition.
  • The textual transcript is used to assign text categories for the call through automated multi-label textual classification.
  • Audio categories for the call are assigned through automated multi-label acoustic classification of the speech signal.
  • An output label for the call is generated based on a combined analysis of the text categories, audio categories, and audio characteristics.
  • The language spoken during the call is detected and used to generate the textual transcript and assign the text categories and audio categories.

Potential applications of this technology:

  • Call centers can use this system to identify potentially fraudulent or unwanted calls, improving security and customer experience.
  • Telecommunication companies can implement this system to automatically filter out unwanted calls, reducing nuisance and spam calls for their customers.
  • Law enforcement agencies can utilize this technology to detect fraudulent or illegal activities during phone calls, aiding in investigations.

Problems solved by this technology:

  • This system helps to identify potentially fraudulent or unwanted calls, saving time and resources by filtering out such calls.
  • It improves the security and privacy of individuals by detecting and preventing fraudulent activities during phone calls.
  • It reduces the annoyance and inconvenience caused by unwanted calls, enhancing the overall phone call experience.

Benefits of this technology:

  • Increased security and fraud prevention in phone calls.
  • Improved customer experience by reducing unwanted calls.
  • Enhanced efficiency and resource utilization for call centers and telecommunication companies.
  • Aid in law enforcement investigations by detecting fraudulent or illegal activities during phone calls.


Original Abstract Submitted

systems and methods for processing calls to determine if the call is potentially fraudulent or unwanted. the system extracts a speech signal from an audio signal associated with a call. the system identifies audio characteristics based on analysis of the audio signal. the system generates textual transcript of the audio signal based on automatic speech recognition of the speech signal, which is used to assign text categories for the call based on an automated multi-label textual classification of the textual transcript. the system assigns audio categories for the call based on automated multi-label acoustic classification of the speech signal. the system generates an output label for the call based on a combined analysis of the text categories, the audio categories, and the audio characteristics. the language spoken during the call may be detected and used to generate the textual transcript and to assign the text categories and the audio categories.

Retrieved from "http://wikipatents.org/index.php?title=20240040035._DETECTION_OF_UNWANTED_CALLS_OR_CALLER_INTENT_BASED_ON_A_FUSION_OF_ACOUSTIC_AND_TEXTUAL_ANALYSIS_OF_CALLS_simplified_abstract_(RealNetworks_LLC)&oldid=30388"