Voice input support program and voice input support device

The voice input support program and device enhance voice recognition accuracy by using multiple engines to compare and correct input data, addressing the challenge of limited specification devices.

JP7877268B2Active Publication Date: 2026-06-22KK TOSHIBA
View PDF 5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
KK TOSHIBA
Filing Date
2023-04-19
Publication Date
2026-06-22

AI Technical Summary

Technical Problem

Voice input devices with limited specifications face challenges in accurately comparing recognition results from different voice recognition engines, especially when the input voice does not contain information representing the item, making it difficult to associate and compare results effectively.

Method used

A voice input support program and device that utilize two speech recognition engines, one for real-time operation and another for comparison, generating and associating recognition results with guidance voice to facilitate easy comparison and correction of input data.

Benefits of technology

Enables accurate and efficient comparison of recognition results, allowing users to identify and correct errors in voice input, even on devices with limited specifications, by presenting differences between recognition outputs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007877268000001
    Figure 0007877268000001
  • Figure 0007877268000002
    Figure 0007877268000002
  • Figure 0007877268000003
    Figure 0007877268000003
Patent Text Reader

Abstract

To provide a speech input support program and a speech input support device that can perform appropriate and easy comparison of recognition results of a speech recognition engine for speech input with the recognition results of another speech recognition engine.SOLUTION: A speech input support program causes a processor to: record speech of a user using a speech input device; perform speech recognition on the recorded speech separately from the speech recognition for inputting a first recorded content using the speech input device; generate a second recorded content based on the recognition results of the separately performed speech recognition and the next action for the user to input using the speech input device; and compare the first recorded content and the second recorded content.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Voice recognition device, voice recognition program, and voice recognition method

    JP2020016839A

  • Voice recognition system, notification method of voice recognition system, program, and mobile body mounted apparatus

    JP2020091435A

  • Information processing device, information processing system, information processing method, and program

    JP2023007960A

  • Information processor, method, and program

    JP2023013585A

  • Speech recognition device, speech recognition program, and speech recognition method

    JP7143665B2