Integrated Speech Recognition Trigger and Speaker Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices with speech recognition capabilities require separate processes and modules for registering trigger words and speakers, leading to inconvenient configurations and increased complexity.
Innovation Solution
An integrated module within the electronic apparatus that receives speech input, extracts phonemic and voice print characteristics, and allows simultaneous registration of trigger words and speakers by analyzing the speech, enabling the device to switch to speech recognition mode based on pre-registered triggers and user authentication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If separate modules are used for registering trigger words and speakers, then each function can be performed independently, but the device complexity increases and the registration process becomes inconvenient
Solution Approach 1:
The patent combines the trigger word registration module and speaker registration module into a single integrated module. This integration allows the system to perform both trigger word recognition and speaker identification simultaneously through a unified interface, eliminating the need for separate registration processes and reducing overall system complexity while maintaining independent functional capabilities.
2Loss of time
If separate processes are used for trigger word registration and speaker registration, then each registration can be completed independently, but the time required for setup increases
Solution Approach 1:
The integrated module performs both trigger word and speaker registration in advance through a single setup process. By completing both registrations preliminarily during one interaction, the system eliminates the need for users to go through separate registration steps later, thereby reducing the overall time required for initial configuration while maintaining ease of operation.
3Adaptability or versatility
If multiple separate modules are equipped in the electronic apparatus, then each function can be optimized independently, but the overall system configuration becomes more complex
Solution Approach 1:
The integrated module is designed to perform multiple functions including trigger word registration, speaker registration, trigger word recognition, and speaker identification within a single unified structure. This multi-functional design maintains the adaptability and versatility of having separate capabilities while significantly reducing the configuration complexity that would result from implementing these same functions through multiple separate modules.
Data Source
AI summary
An electronic apparatus and a method of speech recognition thereof are disclosed. According to the method of speech recognition of the electronic apparatus, the method includes receiving a speech of a speaker, extracting phonemic characteristics for recognizing a speech and voice print characteristics for registering the speaker by analyzing the received speech of the speaker, and in response to the speech of the speaker corresponding a registered trigger word or phrase, based on the extracted phonemic characteristics, changing an execution mode to a speech recognition mode of the electronic apparatus and registering the extracted voice print characteristics as voice print characteristics of the speaker who spoke the speech.