Sound Interface Device Using Acoustic Resonance for Command Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users find it troublesome to operate electronic devices via speech recognition systems, as they need to explicitly speak a fixed trigger word and command content, which can be cumbersome.

Innovation Solution

A user interface device and method that includes a sound input unit, sound recognition unit, speech generation unit, and speech output unit, allowing operation of devices through predetermined sounds, such as musical instrument sounds, which can serve as trigger sounds or command sounds, enabling device control without the need for explicit trigger words or command phrases.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a speech recognition system requires users to speak fixed trigger words and command content, then the system can accurately recognize and execute commands, but the operation process becomes troublesome and cumbersome

Engineering Contradiction:

Improvecommand recognition accuracyVSAvoidoperation convenience

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The patent replaces the mechanical speech-based interaction system with an acoustic resonance-based system. Instead of requiring users to speak trigger words and commands, the system uses acoustic resonance to detect and execute commands through sound frequency matching. This substitution eliminates the need for verbal commands while maintaining reliable command recognition.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the parameter of command input from linguistic content (trigger words and commands) to acoustic frequency parameters. By detecting specific frequency ranges and resonance patterns, the system identifies commands without requiring users to speak predetermined phrases, thus improving ease of operation while maintaining recognition accuracy.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If users must speak specific trigger words and command content in order, then the speech recognition system can process commands correctly, but the operation time and complexity increase

Engineering Contradiction:

Improvecommand processing accuracyVSAvoidcommand execution time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces the sequential speech processing mechanism with a parallel acoustic resonance detection mechanism. Multiple command frequencies can be detected simultaneously through resonance, eliminating the need for sequential trigger word followed by command speech, thus reducing execution time while maintaining accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent pre-establishes acoustic resonance patterns for different commands. When a sound is input, the system immediately matches it against pre-configured resonance patterns, eliminating the need for sequential processing of trigger words and commands. This preliminary preparation of recognition patterns speeds up command execution.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10592204B2User interface device and method, and sound-enabled operation system

Publication Date: 2020.03.17 YAMAHA CORP

AI summary

A user interface device includes a sound input unit which acquires an inputted sound, a sound recognition unit which acquires a result of predetermined recognition processing on the acquired sound, a speech generation unit which generates a speech corresponding to the result of the recognition processing, and a speech output unit which outputs the speech generated by the speech generation unit.