AI Speech Therapy Progression for Stuttering Fluency Training
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing stuttering therapies are costly, time-consuming, and often require in-person attendance, with mixed success in improving long-term fluency, and hardware-based systems are expensive and not widely utilized.
Innovation Solution
A computer-based speech therapy system using artificial intelligence to provide graduated speaking exercises with increasing conversational realism, allowing users to practice fluency in controlled environments before engaging with real-time human interactions, leveraging VR technology to incrementally increase conversational stress.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If in-person speech therapy programs are used, then speech fluency improvement is achieved, but cost and time consumption increase significantly
Solution Approach 1:
The patent creates virtual copies of therapeutic speaking exercises and conversational scenarios that can be accessed digitally. These virtual environments replicate the fluency-building exercises of in-person therapy, allowing users to practice speech fluency through computer-based simulations without requiring physical presence at therapy sessions.
Solution Approach 2:
The patent introduces computer-based software and virtual reality environments as intermediaries between the user and therapeutic intervention. These digital intermediaries deliver structured speaking exercises, provide real-time feedback, and create simulated conversational scenarios, replacing the need for direct in-person therapist interaction while maintaining therapeutic effectiveness.
2Reliability
If hardware-based speech therapy systems are deployed, then speech fluency training is provided, but device cost and complexity increase
Solution Approach 1:
The patent replaces complex hardware-based speech therapy systems with software-based solutions running on standard computers. Instead of requiring specialized electronic devices with sensors and processing units, the therapeutic functionality is delivered through software applications that utilize the existing computational capabilities of personal computers and mobile devices.
Solution Approach 2:
The patent designs the speech therapy system to run on general-purpose computers and mobile devices, making the therapy accessible across multiple platforms without requiring dedicated hardware. The same software application can function on desktop computers, laptops, tablets, and smartphones, eliminating the need for specialized equipment while maintaining therapeutic capabilities.
3Reliability
If graduated speaking exercises with increasing conversational realism are implemented, then long-term fluency improvement is achieved, but program complexity increases
Solution Approach 1:
The patent divides the speech therapy program into segmented levels or stages, each focusing on specific speaking skills and conversational scenarios. Users progress through these structured segments sequentially, with each level building upon previous skills. This segmentation manages program complexity by breaking down the overall therapy into manageable, progressively difficult components.
Solution Approach 2:
The patent implements dynamic adjustment of exercise difficulty and conversational realism based on user performance. The system adapts the complexity of speaking exercises in real-time, increasing conversational realism and difficulty as users demonstrate improved fluency, while providing support at lower complexity levels when users struggle. This dynamic approach manages program complexity by automatically adjusting to user needs.
Data Source
AI summary
A speech therapy system and method therefor are disclosed. The system includes graduated speaking exercise modules and a computer system including a processor and a memory. The modules are arranged sequentially and are collectively configured to provide graduated speaking exercises, or GSEs, of increasing conversational realism for a stuttering user. The processor executes the app and the modules, and each of the modules create an associated GSE that defines a different state of the app. When the app is in a current state defined by a current GSE, the app obtains or determines a fluency metric from user speech or from a user fluency self-rating. When the metric meets an upper fluency threshold of the current GSE, the app transitions to a next app state defined by a next GSE, and the app can conclude that the user is fluent if the upper threshold is met for a final GSE.