Multi-Microphone Speech Recognition Control Device

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing speech recognition control devices struggle to execute multiple execution commands simultaneously when multiple users speak, either limiting functionality to the driver or failing to process commands correctly in multi-user scenarios.

Innovation Solution

A speech recognition control device with multiple microphones placed at different positions and a speech transmission control unit that assigns ranks based on time data or command signal reception order, allowing simultaneous execution of commands by transmitting speech data signals in a predetermined order for processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If only one speech recognition start switch is provided at the driver seat, then the device complexity is reduced, but the adaptability for multiple users deteriorates

Engineering Contradiction:
Improvenumber of speech recognition start switchesVSAvoidability to serve multiple users
Core Design Contradiction:
Device complexityVSAdaptability or versatility

Solution Approach 1:

The speech recognition control device is designed to handle multiple users through a single switch by implementing multi-functionality. The system can identify different users and process their speech commands sequentially, allowing one physical switch to serve multiple users rather than requiring dedicated switches for each user.

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

Solution Approach 2:

The system performs preliminary actions by detecting speech start signals and temporarily storing speech data before full processing. When multiple users speak simultaneously, the system has already captured the speech data in temporary storage, enabling it to process multiple commands in sequence rather than losing any speech input.

Inventive Principle:
Principle #10Preliminary action

2Device complexity

If speech recognition is designed for single-user operation, then the device complexity is reduced, but the productivity when multiple users speak simultaneously deteriorates

Engineering Contradiction:
Improvespeech processing system complexityVSAvoidnumber of execution commands processed
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The system performs preliminary speech detection and temporary storage before full recognition processing. This allows multiple speech inputs to be captured and held in temporary storage simultaneously, ready for sequential processing, thereby maintaining productivity when multiple users speak without significantly increasing system complexity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The speech recognition system dynamically adjusts its processing based on input conditions. When multiple speech signals are detected, the system dynamically switches between temporary storage mode and sequential processing mode, optimizing its operation to handle multiple commands while maintaining manageable complexity.

Inventive Principle:
Principle #15Dynamics

3Adaptability or versatility

If selective signal output from multiple speech recognition start switches is implemented, then the adaptability for multiple users is improved, but the productivity when speeches are input simultaneously deteriorates

Engineering Contradiction:
Improvemulti-user operation capabilityVSAvoidexecution command processing capability
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The system performs preliminary detection of speech start signals from multiple switches and temporarily stores the corresponding speech data before execution. This preliminary action ensures that when multiple users speak simultaneously, all speech data is preserved and ready for sequential processing, maintaining both multi-user adaptability and command processing productivity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system introduces an intermediary temporary storage mechanism between speech input and execution. This intermediary buffer allows multiple speech signals to be accommodated simultaneously, mediating between the need for multi-user support and the requirement for sequential processing capability.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS9830906B2Speech recognition control device
Publication Date: 2017.11.28 KOJIMA INDUSTRIES CORP
  • US9830906B2 patent drawing
  • US9830906B2 patent drawing
  • US9830906B2 patent drawing

AI summary

A speech recognition control device has a plurality of microphones placed at different positions, a speech transmission control unit, and a speech recognition execution control unit. The speech transmission control unit stores data based on the speeches which are input from the microphones and time data related to ranks among the microphones, assigns ranks to the plurality of microphones using the time data based on a preset condition, and transmits a speech data signal corresponding to the microphone to the speech recognition execution control unit in the order of the ranks. The speech recognition execution control unit executes the speech recognition process according to the order of the speech data signals transmitted from the speech transmission control unit.