Audio Call to Action Address Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current speech recognition software cannot extract addressing information from calls to action within audio signals, making it difficult for listeners to respond to invitations or interactions, especially in distracting environments like driving or exercising.

Innovation Solution

A system that uses a mobile communication device to monitor audio signals, digitize them, and analyze spoken content to detect calls to action, extracting addressing and response content information for storage and later use in preparing electronic messages or populating contact fields.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If speech recognition software is used to recognize spoken words, then spoken content can be displayed in a word processing program, but the software cannot extract addressing information from calls to action within audio signals

Engineering Contradiction:

Improveaddressing information extraction capabilityVSAvoidsoftware functionality scope

Core Design Contradiction:

Loss of informationVSAdaptability or versatility

Solution Approach 1:

The patent extracts addressing information (such as phone numbers, URLs, email addresses) from audio signals by separating this specific function from general speech recognition. The system identifies calls to action within spoken content and pulls out relevant addressing information for automated response, making the software versatile enough to handle both speech-to-text conversion and information extraction tasks

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system combines multiple functions into a single platform: speech recognition for displaying spoken words, call to action detection for identifying invitations or requests, and addressing information extraction for retrieving contact details. This multi-functional approach allows the software to serve diverse purposes including transcription, information extraction, and automated response generation

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Reliability

If a listener tries to record or remember addressing information manually, then the information can be retained for response, but this becomes especially difficult when the listener is engaged in another activity while listening

Engineering Contradiction:

Improveinformation retention accuracyVSAvoidlistener burden

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system performs automatic information extraction and response preparation without requiring manual listener intervention. The software autonomously detects calls to action, extracts addressing information, and prepares response messages, freeing the listener from the burden of manual recording while maintaining high accuracy in information retention

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary extraction and organization of addressing information before the listener needs to respond. By pre-processing the audio content and preparing response drafts in advance, the system ensures accurate information retention is available when the listener is ready to act, without requiring intensive cognitive effort during the listening process

Inventive Principle:

Principle #10Preliminary action

3Extent of automation

If speech recognition software responds to predefined keyword instructions, then specific commands can be executed, but the software does not include the ability to extract addressing information provided in conjunction with calls to action

Engineering Contradiction:

Improveresponse automation capabilityVSAvoidinformation processing scope

Core Design Contradiction:

Extent of automationVSAdaptability or versatility

Solution Approach 1:

The patent extracts addressing information from within the audio signal by separating this specific function from general speech recognition. The system identifies calls to action within spoken content and pulls out relevant addressing information for automated response, making the software versatile enough to handle both speech-to-text conversion and information extraction tasks

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS9147403B2Responding to a call to action contained in an audio signal

Publication Date: 2015.09.29 QUALCOMM INC

AI summary

An audio signal is monitored to detect the presence of a call to action contained therein. Addressing information is automatically extracted from the call to action and stored on a storage medium. An electronic message responding to the call to action may be automatically prepared, or a contact field may be automatically populated for inclusion in a contact list. The audio signal may be digitized or obtained from a broadcast transmission, and the process may be performed by a mobile communication device, a central system, or a combination thereof.