Adaptive Transcription Technique Selection via User Feedback

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing transcription systems for hard-of-hearing or deaf individuals do not effectively adapt to user preferences, leading to suboptimal transcription quality as they rely solely on initial transcription generation techniques without considering user feedback.

Innovation Solution

A system that obtains user ratings for transcriptions from multiple communication sessions and selects a different transcription generation technique based on these ratings, switching from fully machine-based automatic speech recognition to re-voicing systems when user satisfaction thresholds are not met, to provide improved transcription display.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a fixed transcription generation technique is used initially, then the system can provide transcription services, but the transcription quality does not adapt to user preferences

Engineering Contradiction:
Improvetranscription quality adaptationVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system dynamically switches between different transcription generation techniques (fully machine-based ASR and re-voicing systems) based on user ratings and satisfaction thresholds. This dynamic adaptation allows the system to optimize transcription quality for each user while maintaining manageable complexity through automated feedback processing.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system implements a feedback mechanism where user ratings of transcriptions are collected and processed to automatically select future transcription techniques. This closed-loop feedback enables continuous improvement of transcription quality without requiring manual system reconfiguration, resolving the contradiction between adaptability and complexity.

Inventive Principle:
Principle #23Feedback

2Reliability

If multiple transcription techniques are maintained for different users, then transcription quality improves, but system complexity increases

Engineering Contradiction:
Improvetranscription qualityVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system changes the operational parameters (transcription technique selection) based on user-specific feedback data. By adjusting which technique is used for each user based on their ratings, the system achieves high reliability for individual users while managing overall complexity through parameter-based differentiation rather than structural complexity.

Inventive Principle:
Principle #35Parameter changes

3Adaptability or versatility

If user feedback is collected and processed, then transcription technique selection improves, but processing time increases

Engineering Contradiction:
Improvetechnique selection accuracyVSAvoidprocessing time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by collecting user ratings during and after communication sessions, processing this feedback data to determine user satisfaction thresholds in advance. This allows the system to have technique selection decisions ready before the next transcription is needed, minimizing processing delays while maintaining high adaptability.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11783837B2Transcription generation technique selection
Publication Date: 2023.10.10 SORENSON IP HOLDINGS LLC
  • US11783837B2 patent drawing
  • US11783837B2 patent drawing
  • US11783837B2 patent drawing

AI summary

According to one or more aspects of the present disclosure, operations related to selecting a transcription generation technique may be disclosed. In some embodiments, the operations may include obtaining multiple user ratings that each correspond to a different one of multiple transcriptions. Each transcription may be obtained using a first transcription generation technique and may correspond to a different one of multiple communication sessions. The operations may further include selecting, for a subsequent communication session that occurs after the multiple communication sessions, a second transcription generation technique based on the user ratings. In addition, the operations may include providing the subsequent transcription to a device during the subsequent communication session.