Voice Recognition Device with Characteristic Component Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Voice recognition devices often erroneously respond to voices other than those uttered by humans, such as television or radio broadcasting, due to the inability to differentiate between human voices and other audio signals.

Innovation Solution

A voice recognition system that superimposes a specific characteristic component on voice signals, allowing the controller to prevent voice recognition processing and response operations when this component is detected, thereby distinguishing human voices from other audio sources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the voice recognition device responds to all voice signals, then the responsiveness to human voice instructions is improved, but erroneous responses to non-human voices such as television or radio broadcasting occur

Engineering Contradiction:
Improveaccuracy of voice recognitionVSAvoiderroneous response to non-human voice
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent applies parameter changes by modifying the voice signal through superimposing a specific characteristic component (such as a specific frequency component or time-domain pattern) onto the voice signal. This transformation creates a distinguishable parameter difference between human-uttered voices and other audio sources like television or radio broadcasting, enabling the recognition device to differentiate and respond appropriately based on the presence or absence of this characteristic component

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent introduces an intermediary mechanism in the form of a characteristic component superimposition system. This intermediary element acts as a marker or tag that mediates between the voice signal and the recognition process, allowing the system to identify whether a voice signal originates from a human utterance or from other sources such as broadcast media, thereby preventing erroneous responses

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If the voice recognition device distinguishes human voice from other audio sources, then erroneous responses are prevented, but the device complexity increases due to additional processing requirements

Engineering Contradiction:
Improveaccuracy of voice recognitionVSAvoidprocessing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent simplifies the overall system complexity by applying parameter changes at the signal level rather than requiring complex analysis of voice characteristics. By superimposing a specific characteristic component with distinct parameters (such as a specific frequency range or temporal pattern), the system achieves reliable differentiation through simple detection of this parameter rather than through complex machine learning or pattern recognition algorithms

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11922953B2Voice recognition device, control method of voice recognition device, content reproducing device, and content transmission/reception system
Publication Date: 2024.03.05 NISSAN MOTOR CO LTD
  • US11922953B2 patent drawing
  • US11922953B2 patent drawing
  • US11922953B2 patent drawing

AI summary

A voice analyzer analyzes whether a voice signal input into a voice input unit includes a specific characteristic component. A voice recognizer recognizes a voice represented by the voice signal input into the voice input unit. A response instruction unit instructs a response to a response operation unit that operates in response to the voice recognized by the voice recognizer. A controller controls the voice recognizer not to execute voice recognition processing by the voice recognizer or controls the response instruction unit not to instruct the response operation unit about an instruction content by the voice recognized by the voice recognizer, when the voice analyzer analyzes that the voice signal includes the specific characteristic component.