Speech Recognition Control Unit for Self-Output Echo Suppression

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing devices with speech recognition functions often incorrectly operate due to speech output by the device itself, leading to unintended commands being issued.

Innovation Solution

A device with a speech recognition function that includes a loudspeaker, microphone, a first speech recognition unit, a command issuance unit, and a control unit, which prohibits command issuance based on speech output from the loudspeaker, using a second speech recognition unit to identify and prevent unintended commands, and optionally employing a downsampler and echo canceller to enhance accuracy and reduce computation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the device uses speech recognition to control operations, then the ease of operation is improved, but the reliability deteriorates due to incorrect operation from self-output speech

Engineering Contradiction:
Improveease of operationVSAvoidreliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent introduces a control unit as an intermediary between the speech recognition unit and the command issuance unit. This control unit monitors speech output from the loudspeaker and selectively blocks commands when self-output speech is detected, thereby preventing incorrect operations while maintaining the ease of speech-based control

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If the device prohibits command issuance based on speech output, then the reliability is improved, but the device complexity increases

Engineering Contradiction:
ImprovereliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The control unit that detects self-output speech and prohibits inappropriate command issuance is integrated into the existing speech recognition system rather than being implemented as a completely separate system. This merging approach adds the necessary reliability function while minimizing the increase in device complexity by utilizing existing system components

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS10262653B2Device including speech recognition function and method of recognizing speech
Publication Date: 2019.04.16 SOCIONEXT INC
  • US10262653B2 patent drawing
  • US10262653B2 patent drawing
  • US10262653B2 patent drawing

AI summary

A device including a speech recognition function which recognizes speech from a user, includes: a loudspeaker which outputs speech to a space; a microphone which collects speech in the space; a first speech recognition unit which recognizes the speech collected by the microphone; a command control unit which issues a command for controlling the device, based on the speech recognized by the first speech recognition unit; and a control unit which prohibits the command issuance unit from issuing the command, based on the speech to be output from the loudspeaker.