Multimodal Record Disambiguation via Feedback Interface
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Multimodal applications face challenges in disambiguating records when a voice utterance identifies multiple records due to homophonic sets, where the same pronunciation corresponds to different words, leading to incorrect selection of records from a database.
Innovation Solution
The multimodal application prompts the user to identify a specific record, receives a voice utterance, determines ambiguity, generates user interaction to disambiguate records based on record attributes, and selects one record for further processing using a disambiguation grammar and user input.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech recognition is used to identify records, then user interaction ease is improved, but record identification accuracy deteriorates due to homophonic sets
Solution Approach 1:
The system implements feedback by detecting when speech recognition results in multiple candidate records and responding by generating a disambiguation interface. The interface presents the ambiguous records to the user and collects additional input until a single record is identified. This feedback loop resolves the accuracy problem while preserving the ease of voice-based interaction.
Solution Approach 2:
The patent introduces an intermediary disambiguation interface between speech recognition and record selection. This intermediary component receives the ambiguous results from speech recognition, processes them through a user-friendly interface, and returns a definitive record selection. The intermediary resolves the contradiction by adding a mediation step that maintains both voice interaction ease and identification accuracy.
2Ease of operation
If multiple input modes are combined, then ease of operation is improved, but device complexity increases
Solution Approach 1:
The disambiguation interface is designed to be universal, handling multiple types of input modes (voice, keyboard, touch) through a single unified component. Rather than creating separate handling logic for each input mode, the system uses one multi-functional interface that adapts to different input types, thereby reducing overall device complexity while maintaining ease of operation across multiple modes.
3Productivity
If voice mode is used for record selection, then productivity is improved, but reliability deteriorates due to ambiguous recognition
Solution Approach 1:
The system performs preliminary action by proactively detecting potential ambiguity in speech recognition results before a final record selection is made. When the speech engine returns multiple candidate records, the system immediately initiates the disambiguation process rather than waiting for an error to occur. This preliminary detection and resolution maintains productivity by preventing failed operations while ensuring reliability through accurate record identification.
Data Source
AI summary
Methods, apparatus, and products are disclosed for record disambiguation in a multimodal application operating on a multimodal device, the multimodal device supporting multiple modes of interaction including at least a voice mode and a visual mode, that include: prompting, by the multimodal application, a user to identify a particular record among a plurality of records; receiving, by the multimodal application in response to the prompt, a voice utterance from the user; determining, by the multimodal application, that the voice utterance ambiguously identifies more than one of the plurality of records; generating, by the multimodal application, a user interaction to disambiguate the records ambiguously identified by the voice utterance in dependence upon record attributes of the records ambiguously identified by the voice utterance; and selecting, by the multimodal application for further processing, one of the records ambiguously identified by the voice utterance in dependence upon the user interaction.