Adaptive Feedback Mode Selection for Natural Speech Dialog

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing information processing systems struggle to provide personalized feedback to users, leading to unnatural interactions and perceived poor technical performance due to fixed feedback schemes that do not adapt to individual user situations.

Innovation Solution

An information processing apparatus that selects feedback modes based on the user's speech style, incorporating both implicit and explicit feedback, with implicit feedback adjusting output styles to improve recognition accuracy without direct user instruction and explicit feedback providing clear improvement methods when necessary.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a fixed feedback scheme is used, then the system operation is simple, but the adaptability to individual users deteriorates

Engineering Contradiction:
Improvesystem operation simplicityVSAvoidadaptability to individual users
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The feedback scheme transitions from a fixed static mode to a dynamic adaptive mode. The system dynamically selects between implicit feedback mode and explicit feedback mode based on real-time recognition accuracy and user speech patterns, enabling the feedback mechanism to adapt to individual users while maintaining operational simplicity through automated mode selection.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If explicit feedback is always provided, then the recognition accuracy improvement is clear, but the naturalness of dialog deteriorates

Engineering Contradiction:
Improverecognition accuracy improvementVSAvoidnaturalness of dialog
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system applies different feedback qualities to different situations. Implicit feedback (subtle, natural) is used when recognition accuracy is sufficient, while explicit feedback (clear, direct) is used when recognition accuracy needs improvement. This localized application of feedback types maintains natural dialog while ensuring recognition accuracy improvement when necessary.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The feedback mode parameter changes dynamically based on recognition accuracy thresholds and user speech style analysis. The system adjusts the feedback parameter between implicit and explicit modes, changing the nature of feedback provided to balance naturalness and recognition improvement effectiveness.

Inventive Principle:
Principle #35Parameter changes

3Ease of operation

If implicit feedback is always used, then the dialog naturalness is maintained, but the recognition accuracy improvement becomes insufficient

Engineering Contradiction:
Improvedialog naturalnessVSAvoidrecognition accuracy improvement
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system implements a dual-mode feedback mechanism where implicit feedback maintains dialog naturalness and explicit feedback ensures recognition accuracy improvement. The feedback loop continuously monitors recognition accuracy and switches between implicit and explicit modes, ensuring that recognition accuracy improvement is sufficient while maintaining naturalness when possible.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS11462213B2Information processing apparatus, information processing method, and program
Publication Date: 2022.10.04 SONY GROUP CORP
  • US11462213B2 patent drawing
  • US11462213B2 patent drawing
  • US11462213B2 patent drawing

AI summary

There is provided an information processing apparatus to realize more natural dialog between users and a system, the information processing apparatus including: a control unit that selects a feedback mode in response to a speech style of a user from among a plurality of modes in accordance with information related to recognition of speech of the user. The plurality of modes include a first mode in which implicit feedback is performed and a second mode in which explicit feedback is performed. Provided is an information processing method including: selecting, by a processor, a feedback mode in response to a speech style of a user from among a plurality of modes in accordance with information related to recognition of speech of the user. The plurality of modes include a first mode in which implicit feedback is performed and a second mode in which explicit feedback is performed.