Audio Analytics System for Accessibility via Real-Time Stream Prioritization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users, especially those with hearing impairments, face difficulties in navigating complex audio environments in digital content such as interactive games due to overwhelming and distracting sound combinations, which can affect their enjoyment and accessibility.

Innovation Solution

A system that monitors audio streams based on a user's custom audio profile, prioritizes and modifies sound properties in real-time to enhance audio accessibility, allowing users to customize the audio experience by boosting important sounds like spoken dialogue over background noise.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple audio streams are presented simultaneously in digital content, then the content becomes more engaging and socially interactive, but the audio environment becomes overwhelming and distracting for users with hearing impairments

Engineering Contradiction:
Improvesocial interaction capabilityVSAvoidaudio distraction
Core Design Contradiction:
Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The system segments the complex audio environment into distinct audio streams (game audio, social audio, real-world audio) and applies individualized processing to each stream based on user profile, allowing selective enhancement or suppression of specific audio categories while maintaining overall engagement

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different audio processing parameters are applied to different audio streams based on their specific characteristics and user preferences, with each stream receiving customized audio modifications tailored to its type and importance to the user

Inventive Principle:
Principle #3Local quality

2Reliability

If audio modifications are applied to prioritize certain sounds, then accessibility for users with hearing impairments is improved, but the complexity of audio processing increases

Engineering Contradiction:
Improveaudio accessibilityVSAvoidaudio processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

User audio profiles and preferences are established in advance through profiling processes, allowing the system to automatically apply appropriate audio modifications without requiring real-time complex decision-making, thereby reducing processing complexity while maintaining accessibility

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

An audio processing system acts as an intermediary between the raw audio streams and the user's hearing device, applying pre-determined modifications based on user profiles, which simplifies the overall processing architecture while ensuring consistent accessibility improvements

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS20230069271A1Audio analytics and accessibility across applications and platforms
Publication Date: 2023.03.02 SONY INTERACTIVE ENTERTAINMENT LLC
  • US20230069271A1 patent drawing
  • US20230069271A1 patent drawing
  • US20230069271A1 patent drawing

AI summary

Systems and methods for audio analytics and audio-based accessibility are provided. A user audio profile may be stored in memory for a user. The user audio profile may include a custom prioritization of one or more audio parameters associated with one or more audio modifications. Audio streams associated with a user device of the user may be monitored based on the user audio profile during a current session. The audio parameters may be detected as being present in the monitored audio streams, and the detected audio parameters may be prioritized based on the custom prioritization of the user audio profile. A sound property of at least one of the audio streams may be modified in real-time based on the prioritization of the detected audio parameters by applying the audio modifications of the user audio profile to the at least one audio stream before the at least one audio stream is provided to the user device.