Speech Recognition Address Book Management for Driving Safety
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing address book management systems do not allow for convenient and easy modification and updating of contact information while driving, as they require manual operation of smartphones, which can compromise driving safety and convenience.
Innovation Solution
An address book management system using speech recognition that connects two terminal devices to communicate and update address book databases based on spoken dialogue, employing speech recognition algorithms like Deep Neural Networks to extract keywords and update contact information without manual operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual operation of smartphone is used to update address book, then contact information can be updated, but driving safety is compromised and operation convenience is reduced
Solution Approach 1:
The patent replaces manual mechanical operations (touching, typing on smartphone) with voice-based acoustic input. The driver speaks contact information updates which are captured by the vehicle's microphone system, processed through speech recognition, and automatically added to the address book, eliminating the need for manual smartphone operation while driving
Solution Approach 2:
The system enables self-service by automatically processing voice inputs into structured contact information. The speech recognition system autonomously extracts names, phone numbers, and other contact details from spoken dialogue, performs validation, and updates the address book without requiring driver intervention or manual confirmation
2Ease of operation
If speech recognition is used to update address book, then operation convenience is improved and driving safety is enhanced, but system complexity increases
Solution Approach 1:
The patent leverages the universal speech recognition capability already present in modern smartphones and vehicles. The system uses existing multi-functional components (microphone, processor, speech recognition software) that serve multiple purposes including voice calls, music control, and now address book management, thereby avoiding additional dedicated hardware complexity
Solution Approach 2:
The patent introduces a communication interface as an intermediary between the vehicle system and the smartphone's existing address book functionality. This mediator handles the speech recognition processing and data formatting, allowing the system to utilize the smartphone's established address book infrastructure without requiring complete system redesign
3Productivity
If speech recognition processing is performed, then contact information can be extracted automatically, but processing time and computational resources are consumed
Solution Approach 1:
The system performs preliminary speech recognition processing during natural conversation periods when the driver is already speaking. Contact information extraction is initiated automatically from the speech stream without requiring separate processing steps, utilizing the existing speech input already captured for other vehicle functions
Solution Approach 2:
The patent applies partial processing by focusing speech recognition efforts only on segments of dialogue that contain contact information updates. The system identifies keywords and contextual cues to trigger targeted extraction processes, rather than continuously processing all speech, thereby reducing overall computational burden while maintaining high extraction efficiency
Data Source
AI summary
Disclosed are an address book management apparatus using speech recognition, a vehicle, an address book management system and an address book management method using the speech recognition. The address book management method may include connecting a first terminal device storing an address book database to a second terminal device storing an address book database to communicate with each other; obtaining a speech signal of at least one of a first user of the first terminal device and a second user of the second terminal device, from the first terminal device; performing speech recognition on at least one speech signal of the first user and the second user; obtaining a first keyword from the at least one speech signal of the first user and the second user, based on a result of the speech recognition; and updating the address book database using the first keyword.