Voice Query Phonetic Confusion Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice recognition systems fail to accurately interpret intended queries due to misrecognition, leading to queries with different meanings than intended, as they rely on spell-corrected language models and may not account for phonetic confusions unique to speech recognition outputs.
Innovation Solution
A voice-recognition system that identifies phonetically confusable segments in textual queries and provides alternative query suggestions based on historical data and speech recognition confidence scores, allowing users to select more accurate queries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If speech recognition is used to transcribe voice queries, then the queries are correctly spelled, but the transcribed words may not be the correct words intended by the speaker
Solution Approach 1:
The system provides alternative query suggestions based on phonetically confusable segments and speech recognition confidence scores, allowing users to feedback and select the intended query, thereby improving word recognition accuracy while maintaining spelling correctness
Solution Approach 2:
The system introduces an intermediary classification layer that identifies phonetically confusable segments between speech recognition output and final query interpretation, mediating between correct spelling and correct word selection
2Reliability
If alternative query suggestions are provided based on phonetic confusion, then query accuracy improves, but system complexity increases
Solution Approach 1:
The system segments the query into individual words and identifies phonetically confusable segments separately, applying phonetic analysis only where needed rather than to the entire query, thus improving accuracy while limiting complexity increase to specific segments
3Reliability
If speech recognition confidence scores are used to determine alternative suggestions, then query interpretation improves, but processing time increases
Solution Approach 1:
The system applies phonetic confusion analysis and alternative suggestion generation only to segments with low speech recognition confidence scores or identified phonetically confusable segments, rather than processing the entire query uniformly, thus improving interpretation accuracy while minimizing additional processing time
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods and systems are provided for providing alternative query suggestions. For example, a spoken natural language expression may be received and converted to a textual query by a speech recognition component. The spoken natural language expression may include one or more words, terms, and/or phrases. A phonetically confusable segment of the textual query may be identified by a classifier component. The classifier component may determine at least one alternative query based on identifying at least the phonetically confusable segment of the textual query. The classifier may further determine whether to suggest the at least one alternative query based on whether the at least one alternative query is sensical and/or useful. When it is determined to suggest the at least one alternative query, the at least one alternative query may be provided to and displayed on a user interface display.