Vehicle Speech Recognition Using Visual Indicators

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users of speech recognition systems in vehicles often struggle to accurately specify control targets due to unfamiliarity with the exact names of vehicle components, leading to unclear user intentions and potential need for subsequent utterances to clarify the control target.

Innovation Solution

A vehicle-based speech recognition system that displays a vehicle image with a graphic object and indicators, allowing users to specify control targets by inputting corresponding indicators, which are mapped to specific components, enabling intuitive selection and control of vehicle functions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the speech recognition system requires users to utter the full name of vehicle components, then the control precision is improved, but the ease of operation deteriorates

Engineering Contradiction:
Improvecontrol target specification accuracyVSAvoiduser utterance convenience
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent introduces visual indicators as an intermediary between the user and the speech recognition system. These indicators provide a visual reference that helps users accurately specify control targets without needing to remember or utter the full component names, thus maintaining control precision while improving ease of operation

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent segments the vehicle interior into multiple regions with distinct indicators. This segmentation allows users to locate and specify control targets more easily by referencing visual indicators rather than relying on verbal precision, resolving the contradiction between accurate specification and ease of use

Inventive Principle:
Principle #1Segmentation

2Ease of operation

If the speech recognition system displays visual indicators to guide users, then the ease of operation is improved, but the device complexity increases

Engineering Contradiction:
Improvecontrol target specification convenienceVSAvoidsystem structure complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent makes the display device serve multiple functions: it displays visual indicators for user guidance and also serves as the interface for the speech recognition system. This multi-functionality approach adds visual guidance capability without requiring separate dedicated components, thus improving ease of operation while minimizing the increase in device complexity

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Measurement precision

If the system requires subsequent utterances to clarify control targets, then the measurement precision is improved, but the loss of time increases

Engineering Contradiction:
Improvecontrol target identification accuracyVSAvoidtime for control target specification
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent displays visual indicators in advance before the user needs to specify a control target. This preliminary visual guidance helps users accurately identify and specify control targets in their initial utterance, eliminating the need for subsequent clarification and thus reducing time loss while maintaining precision

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20230206918A1Speech Recognition System and Method for Providing Speech Recognition Service
Publication Date: 2023.06.29 HYUNDAI MOTOR CO LTD
  • US20230206918A1 patent drawing
  • US20230206918A1 patent drawing
  • US20230206918A1 patent drawing

AI summary

A vehicle may include: a display provided inside the vehicle; and a controller configured to control the display, based on a condition being satisfied, to display a vehicle image comprising a graphic object and a plurality of indicators, wherein the graphic object indicates a plurality of portions of the vehicle image, and wherein each of the plurality of indicators is respectively associated with one of the plurality of portions. Based on a user utterance associated with at least one indicator of the plurality of indicators, the controller may be configured to control a control target corresponding to the at least one indicator.