Intermediate Speech Transcription Display for ASR Editing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automatic Speech Recognition (ASR) systems often provide varying levels of recognition accuracy, leading to multiple transcription options for a single utterance, which can be tedious for users to navigate, especially on small display devices where only the highest confidence results are typically displayed.
Innovation Solution
The method involves temporarily displaying intermediate speech transcription results alongside final results on user devices, allowing users to view and edit all transcription options, including displaying them as a drop-down list ordered by confidence levels, enabling easier correction of transcription errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If only the highest confidence transcription results are displayed on small devices, then the display space is sufficient, but the user cannot view or edit all transcription options easily
Solution Approach 1:
The patent segments the transcription results by confidence levels, displaying only the top N results (e.g., top 3) on the small device screen. This segmentation allows the system to fit multiple transcription options within limited display space while still providing users with meaningful alternatives for correction, resolving the contradiction between display area constraints and editing accessibility.
2Ease of operation
If all transcription options are displayed to allow easy correction, then the ease of operation improves, but the device complexity increases due to navigation requirements
Solution Approach 1:
The patent applies partial action by displaying only a subset of transcription results (the top N highest confidence results) rather than all possible options. This partial display provides users with sufficient information to make corrections without requiring complex navigation interfaces to browse through exhaustive lists, thus improving ease of operation while avoiding excessive device complexity.
3Loss of information
If multiple transcription results are displayed simultaneously, then the information completeness improves, but the readability and user focus deteriorate due to cluttered interface
Solution Approach 1:
The patent applies local quality by varying the display presentation based on the confidence level of each transcription result. Higher confidence results are displayed with greater prominence (e.g., larger font, different styling), while lower confidence results are displayed with less prominence. This differential presentation maintains information completeness while preserving interface clarity and user focus on the most likely correct transcription.
Data Source
AI summary
A communication system includes at least one transmitting device and at least one receiving device, one or more network systems for connecting the transmitting device to the receiving device, and an automatic speech recognition (“ASR”) system, including an ASR engine. A user speaks an utterance into the transmitting device, and the recorded speech audio is sent to the ASR engine. The ASR engine returns intermediate transcription results to the transmitting device, which displays the intermediate transcription results in real-time to the user. The intermediate transcription results are also correlated by utterance fragment to final transcription results and displayed to the user. The user may use the information thus presented to make decisions as to whether to edit the final transcription results or to speak the utterance again, thereby repeating the process. The intermediate transcription results may also be used by the user to edit the final transcription results.