Captioned Telephone System With Text-To-Speech And Answer Assistance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Captioned telephone service users with hearing loss face challenges in being understood during phone calls, particularly when their speech is difficult to comprehend, leading to prolonged interactions and issues with interactive voice response systems.
Innovation Solution
A captioned telephone system incorporating text-to-speech functionality to convert user text input into speech and an answer assistance system that analyzes peer voice to generate answer suggestions, enhancing communication accuracy and timeliness while protecting user privacy by processing data locally on the user device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the CTS system uses traditional speech-to-text transcription only, then the system structure remains simple, but the CTS user's difficult-to-understand speech cannot be properly converted, leading to communication failures and prolonged call duration
Solution Approach 1:
The patent combines text-to-speech conversion and answer assistance functions with the traditional captioned telephone service system. The TTS system converts the CTS user's text input into speech that the peer can understand, while the answer assistance system provides suggested responses. This merging of multiple functions resolves the contradiction by improving communication reliability through multiple conversion pathways while integrating these features into an unified system architecture.
Solution Approach 2:
The patent introduces intermediate processing systems - the TTS system acts as an intermediary converting text to speech, and the answer assistance system serves as a mediator providing suggested responses. These intermediary components bridge the gap between the CTS user's difficult speech and the peer's understanding, improving communication accuracy while maintaining manageable system complexity through modular design.
2Productivity
If the CTS system adds TTS and answer assistance functions, then communication accuracy and timeliness improve, but the system complexity increases
Solution Approach 1:
The patent segments the enhanced CTS system into distinct functional modules: the captioner system for transcription, the TTS system for text-to-speech conversion, and the answer assistance system for generating suggested responses. Each module operates independently with defined interfaces, improving communication efficiency through specialized processing while controlling system complexity through modular architecture that allows independent development and maintenance of each component.
3Object-affected harmful factors
If the system processes user data locally on the device, then personal information security improves, but the processing capability and response time may be limited
Solution Approach 1:
The patent implements local processing of the CTS user's personal information and data on the user's device rather than centralized cloud processing. This local quality approach ensures that sensitive information remains on the user's device, improving information security. The processing power requirement is managed by optimizing local algorithms and selectively processing only necessary data locally while maintaining the ability to access additional resources when needed.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate, timely, and effective communication for users with difficult-to-understand speech, reducing call duration and avoiding unintended terminations, while ensuring personal information security and intuitive user interfaces.
Implementation Method 1
The CTS system's TTS system converts the CTS user's text input into speech, and transfers the voice of the speech to the peer's device in real time via the voice path
Implementation Method 2
The CTS system's answer assistance system analyzes the peer's voice to identify a question, analyzes the question to generate answer suggestions
Data Source
AI summary
A captioned telephone service system having the text-to-speech and answer assistance functions includes a captioner, a text-to-speech system, and an answer assistance system. The captioner provides captions to a user during a phone call between the user and a peer by receiving the peer's voice from a peer device, transcribing the peer's voice into caption data, and transferring the caption data to the user device. The text-to-speech system is configured to receive text data from the user device, convert the text data into speech, and transfer the voice of the speech to the peer device via the voice path in real time. The answer assistance system is configured to receive the caption data from the captioner, analyze the caption data to identify a question, analyze the question to generate answer suggestions, and forward the answer suggestions to the user device for review, editing, and selection.