Utterer Selection Interface for Precise Speech Association

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems face challenges in accurately associating an utterance with its utterer due to the utterer's focus on their own utterance, leading to low precision in identifying the speaker.

Innovation Solution

An information processing system that includes a processor to acquire operation information from an operation device, allowing a selector to choose an utterer from among multiple candidates and associate the utterance with the specified individual based on acquired data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If each candidate operates their own operation device to make a declaration, then the system can capture utterance information, but the precision of associating the utterance with the correct utterer decreases because the utterer focuses on their own utterance and may forget to make a declaration or declare at the wrong timing

Engineering Contradiction:

Improveprecision of association between utterance and uttererVSAvoidease of making a declaration

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system introduces a third party (the selector operating a shared operation device) as an intermediary to bridge the gap between utterance detection and utterer identification. Instead of relying on the utterer themselves to declare their identity, the selector observes who is speaking and manually associates the utterance with the correct person, eliminating the timing and attention issues that plague self-declaration systems.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements a feedback mechanism where the selector receives real-time information about who is speaking (through audio sensing) and manually confirms the association between the utterance and the utterer. This feedback loop allows for correction and verification, ensuring accurate association even when the utterer is focused on their own speech.

Inventive Principle:

Principle #23Feedback

2Reliability

If the utterer makes a self-declaration, then the system can identify the utterer, but timing mismatches and forgotten declarations reduce the reliability of the association

Engineering Contradiction:

Improvereliability of utterance-utterer associationVSAvoidtiming discrepancy between utterance and declaration

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The selector acts as an independent intermediary who objectively observes the speaking person and manually associates the utterance with the correct utterer. This eliminates the reliability issues of self-declaration systems where timing mismatches and forgotten declarations occur, as the selector's manual association is not constrained by the utterer's attention or timing.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary action by detecting who is speaking before the declaration process begins. The audio sensing unit identifies the utterer in advance, and the selector can immediately associate the utterance with the correct person, eliminating timing delays and ensuring reliable association without waiting for the utterer to self-identify.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250377910A1Information processing system, operation device, and non-transitory computer readable medium storing program

Publication Date: 2025.12.11 FUJIFILM BUSINESS INNOVATION CORP

AI summary

An information processing system includes a processor configured to acquire operation information of an operation device that is configured such that each of plural candidates who possibly make an utterance is selectable and that is operated by a selector in a case where the selector selects an utterer from among the plural candidates, specify the utterer from among the plural candidates based on the acquired operation information, and associate the specified utterer with an utterance that is made in a case where the operation device is operated by the selector.