Vehicle Speech Output Directivity for Multi-User Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional speech recognition devices for vehicles fail to distinguish between multiple users during conference calls and text messaging, making it difficult for users to recognize conversation partners during multi-conversation modes.
Innovation Solution
A method and system that utilize sound directivity and surround sound functions to allocate sound spaces based on user information, assigning directivity to speech and outputting it to specific spaces, allowing easy recognition of conversation partners by arranging conversation partners in allocated spaces and controlling speech output timing and speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech is output without distinguishing users during multi-conversation mode, then the system operates simply, but users cannot easily recognize conversation partners
Solution Approach 1:
The speech output system is segmented by assigning different spatial positions to different conversation partners. The speaker arrangement unit divides the speaker array into multiple groups, each corresponding to a specific sound space, and assigns speech to different groups based on the conversation partner's position. This spatial segmentation enables users to easily identify conversation partners through directional sound without requiring complex user interface modifications.
Solution Approach 2:
Different regions of the speaker array are assigned different functions corresponding to different conversation partners. Each speaker or speaker group is configured with specific directivity patterns and spatial characteristics tailored to its associated conversation partner's position. This local differentiation of speaker properties enables precise spatial audio output that helps users identify speakers based on sound direction.
2Adaptability or versatility
If multiple conversation partners are supported simultaneously, then communication versatility improves, but speech output timing becomes complex
Solution Approach 1:
The system pre-calculates and stores directivity patterns, speaker arrangements, and timing parameters for multiple conversation partners before actual speech output. The speaker arrangement unit prepares multiple speaker group configurations in advance, each optimized for a specific conversation partner's position. When speech needs to be output, the system simply selects from pre-prepared configurations rather than calculating them in real-time, reducing computational complexity during active communication.
Solution Approach 2:
The speech output system dynamically adjusts speaker selection, directivity patterns, and timing based on real-time detection of conversation partner positions and speech timing requirements. The system flexibly switches between different speaker arrangements and directivity configurations to accommodate multiple conversation partners simultaneously, optimizing speech output for each partner's spatial location while maintaining overall system coordination.
Data Source
AI summary
A method for supporting a multi-conversation mode for a vehicle of the present disclosure may include: receiving user information of the multi-conversation mode and at least one of a message or speech from a conversation partner participating in the multi-conversation mode; allocating sound spaces on the basis of the user information; and assigning directivity to speech generated on the basis of at least one of the message or the speech and outputting the speech to an allocated space.