Mobile Speech Control for Non-Voice Terminals With User Verification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Many devices, such as smart televisions and conference terminals, lack native support for speech control, making the control process complex and user experience poor.

Innovation Solution

A speech control system that utilizes a mobile terminal with a microphone array to collect speech data, performs recognition, and interacts with a server to control devices lacking native speech capabilities, ensuring security through user verification and reducing the need for device reconstruction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If speech control is implemented on devices without native support, then speech control capability is achieved, but device complexity and reconstruction costs increase

Engineering Contradiction:
Improvespeech control capabilityVSAvoiddevice reconstruction
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces a server as an intermediary component that handles speech recognition and control instruction generation. The terminal device only needs to communicate with this server, avoiding the need to integrate complex speech recognition engines directly into the terminal. This mediator approach enables speech control capability while keeping the terminal device structure simple and avoiding reconstruction.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If speech control is enabled on existing devices, then control flexibility improves, but security risks increase due to unauthorized access

Engineering Contradiction:
Improvecontrol flexibilityVSAvoidsecurity
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent implements preliminary identity verification through the server before executing speech control commands. The server authenticates user identity and verifies permissions in advance, ensuring that only authorized users can control the terminal device. This preliminary security check maintains control flexibility while preventing unauthorized access and ensuring system reliability.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If devices are reconstructed to support speech control, then native speech support is achieved, but costs and implementation time increase

Engineering Contradiction:
Improvenative speech supportVSAvoidreconstruction cost
Core Design Contradiction:
Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

The patent creates a universal speech control system where a single server can provide speech recognition services to multiple different terminal devices. Instead of equipping each device with its own speech recognition capabilities, the server serves multiple devices universally, achieving native speech support functionality while significantly reducing manufacturing and implementation costs.

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

Data Source

PatentUS12524514B2Speech control system and method, apparatus, device, medium, and program product
Publication Date: 2026.01.13 HUAWEI TECH CO LTD
  • US12524514B2 patent drawing
  • US12524514B2 patent drawing
  • US12524514B2 patent drawing

AI summary

A speech control system includes a first client running on a mobile terminal, a server end running on a server, and a second client running on a controlled terminal. The first client obtains identity information of a user, and sends the identity information of the user to the server end. The server end verifies the identity information of the user. The first client further collects speech data of the user, generates a speech control request based on the speech data, and sends the speech control request to the server end. When verification on the identity information succeeds, the server end generates a control instruction based on the speech control request, and sends the control instruction to the second client. The second client indicates the controlled terminal to execute the control instruction.