IoT Device Control via Lombard Effect Speech Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies fail to accurately select and operate specific IoT electronic devices among multiple devices, leading to unintended activation of nearby devices when a user attempts to call a device located far away without clear context information.
Innovation Solution
A method using a speech recognition neural network that analyzes user utterance styles, including Lombard effect features such as pronunciation stress, pitch, and pause sections, to determine the intended device, allowing operation of devices far away from the user without additional context.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a user utters a calling speech to operate an IoT electronic device located far away, then the device located far away should be activated, but other electronic devices located nearby are also activated due to unclear context relationship information
Solution Approach 1:
The patent analyzes changes in speech parameters (Lombard effect features) to determine the intended device. By detecting parameters such as pronunciation stress, pitch, and pause sections that change when a user calls a distant device, the system can accurately identify the target device among multiple electronic devices without requiring the user to move closer or provide additional context.
Solution Approach 2:
The patent introduces an intermediary mechanism that uses speech feature analysis as a mediator between the user's calling speech and the device selection process. The speech recognition neural network analyzes Lombard effect features as an intermediate step to determine which device the user intends to operate, enabling accurate device selection without direct spatial proximity requirements.
2Measurement precision
If the user moves adjacent to the specific electronic device to ensure accurate selection, then the correct device can be operated, but the user convenience and operation speed are reduced
Solution Approach 1:
The system detects parameter changes in the user's speech when calling a distant device. By analyzing Lombard effect features (pronunciation stress, pitch, pause sections), the system can accurately identify the intended device without requiring the user to physically move closer, thereby maintaining both accuracy and operation speed.
3Reliability
If the user continuously utters the calling speech until the specific device is activated, then the correct device can be operated, but the operation efficiency and user convenience are reduced
Solution Approach 1:
The patent uses speech parameter analysis to reliably determine the intended device from the first utterance. By detecting Lombard effect features that indicate distant device communication, the system achieves reliable device activation without requiring repeated utterances, thereby maintaining high operation efficiency.
Data Source
AI summary
A method and apparatus for controlling a device according to an embodiment of the present disclosure may be based on a speech feature of a user reflecting the Lombard effect so as to operate a device located far away from the user, among a plurality of electronic devices. As such, even when the user calls a device located far away from the user without any separate context information, speech recognition neural networks and weight calculation neural networks may be selected and used to operate the device located far away from the user, and reception of a speech signal of the user calling a device located far away from the user may be performed in an Internet of Things (IoT) environment using a 5G network.