Active Sound Design System Using Refresh Rate Input Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing active sound design (ASD) systems in electric vehicles face challenges in providing customizable and responsive sound experiences without increasing computing load and cost, as customers desire personalized and real-time sound adjustments that current systems struggle to deliver efficiently.
Innovation Solution
A system utilizing a deep learning model that categorizes inputs as fast and slow refresh rate inputs, assigning processing resources accordingly, with fast inputs directly operating the wave synthesis ASD module for immediate response and slow inputs adjusting model weights for stem generation, allowing for customizable and responsive sound generation with reduced computational demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the responsiveness of ASD is increased to meet customer demands for real-time sound adjustments, then the responsiveness is improved, but the computing load increases
Solution Approach 1:
The patent segments inputs into two categories: fast refresh rate inputs (FRRIs) requiring immediate processing for real-time responsiveness, and slow refresh rate inputs (SRRIs) that can be processed asynchronously. This segmentation allows the system to maintain high responsiveness for critical sound parameters while reducing overall computing load by deferring non-critical processing.
Solution Approach 2:
The system performs preliminary actions by pre-processing slow refresh rate inputs and pre-generating sound stems in advance, storing them for later use. This allows the wave synthesis module to operate with minimal latency when FRRIs arrive, maintaining responsiveness without requiring continuous high computing power.
2Adaptability or versatility
If more processing resources are assigned to achieve personalized and customizable sound designs, then the adaptability is improved, but the device complexity increases
Solution Approach 1:
The patent uses copying by generating sound stems from slow refresh rate inputs and storing them in a library for repeated use. Instead of processing every sound request in real-time, the system creates reusable sound templates that can be quickly instantiated and modified for personalized sound designs, reducing computational complexity while maintaining adaptability.
Solution Approach 2:
The system implements dynamic resource allocation where processing power is dynamically assigned based on input refresh rates. Fast refresh rate inputs receive immediate processing attention for real-time customization, while slow refresh rate inputs are processed when computational resources are available, allowing the system to adapt to varying customization demands without requiring peak computing resources continuously.
Data Source
AI summary
Systems and methods for active sound design (ASD) generation are provided. The system may comprise one or more speakers and a computing device, comprising a processor and a memory. The memory may be configured to store instructions that, when executed by the processor, are configured to cause the processor to receive one or more inputs for synthetic sound generation, classify the one or more inputs as fast refresh rate inputs (FRRIs) or slow refresh rate inputs (SRRIs), assign one or more processing resources as a function of refresh rate, generate ASD based on the one or more inputs, and play the synthetic sound on the one or more speakers.