Semi-randomized Audio Generation for Interactive Toys

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing toys and characters with prerecorded audio effects are limited in interactivity and immersion due to high costs and restricted sound outputs, and require extensive scripting and voice acting for complex interactions, which restricts their ability to become truly interactive and immersive.

Innovation Solution

A method that selects a communication pattern with a degree of randomness to generate semi-randomized conversations by identifying and modifying audio profiles from predefined audio files, allowing devices to interact dynamically and reduce the need for extensive scripting and voice acting.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If prerecorded phrases and audio effects are used to increase immersion, then user immersion is improved, but device complexity and production costs increase due to voice actors and complex audio mixing

Engineering Contradiction:

Improveproduction costVSAvoidimmersion quality

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

The patent uses text-to-speech synthesis to generate speech audio programmatically, copying the function of voice actors through software-based speech generation rather than recorded human voices. This eliminates the need for expensive voice acting while maintaining immersive audio output.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical system of recording studios, voice actors, and physical audio mixing with an automated software system that programmatically generates and mixes audio outputs. This substitution dramatically reduces production costs while maintaining audio quality.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If a restricted set of prerecorded phrases is used, then production costs are reduced, but interactivity and immersion are drastically limited

Engineering Contradiction:

ImproveinteractivityVSAvoidaudio content library

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic audio generation where the system adapts its speech outputs in real-time based on user interactions, device state, and contextual parameters. This creates unlimited interactivity without requiring a pre-recorded library, as the audio is generated on-demand through text-to-speech synthesis.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent changes the fundamental parameter of audio content from static prerecorded phrases to dynamically generated speech. By controlling text-to-speech parameters (text input, voice selection, pitch, volume, timing), the system achieves high adaptability without maintaining large audio libraries.

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If multiple conversational scripts are prepared for device interactions, then device interactivity is improved, but production costs significantly increase due to extensive voice acting requirements

Engineering Contradiction:

Improvedevice interactivityVSAvoidscript production

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal text-to-speech system that can handle all conversational scenarios across multiple devices through a single platform. Instead of recording separate scripts for each device combination, the system programmatically generates appropriate speech for any interaction scenario, making the solution universally applicable to all device pairs.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system uses automated text-to-speech synthesis to generate all conversational content without human voice actors. The devices themselves serve the function of creating their own speech outputs through programmable text processing and synthesis, eliminating the need for external production resources.

Inventive Principle:

Principle #25Self-service

4Adaptability or versatility

If scripted and prerecorded content is used for device interactions, then some level of interaction is achieved, but true interactivity and immersion are prevented due to content limitations

Engineering Contradiction:

Improvetrue interactivityVSAvoidcontent variety

Core Design Contradiction:

Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

The patent transforms the static nature of scripted content into dynamic, real-time speech generation. The system adapts its responses based on current interaction context, user input, and device state, creating truly interactive experiences rather than playing predetermined recordings. This dynamic generation provides unlimited content variety without physical content constraints.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS10981073B2Localized and standalone semi-randomized character conversations

Publication Date: 2021.04.20 DISNEY ENTERPRISES INC

AI summary

Techniques for randomized device interaction are provided. A first communication pattern is selected, with at least a degree of randomness, from a plurality of communication patterns, where each of the plurality of communication patterns specifies one or more audio profiles. A first audio profile specified in the first communication pattern is identified. A first portion of audio is extracted from a first audio file with at least a degree of randomness, and the first portion of audio is modified based on the first audio profile. Finally, the first modified portion of audio is outputted by a first device.