Voice Query Correction via Pronunciation Rate Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional media guidance applications often misinterpret voice queries, leading users to repeat entire queries to correct errors, which is frustrating and time-consuming.
Innovation Solution
The system corrects voice queries by analyzing the pronunciation rate of subsequent queries, identifying misinterpreted words based on pronunciation time, and generating an adjusted query to correct the initial query.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the media guidance application uses voice recognition to process user queries, then the ease of operation is improved, but the measurement precision deteriorates due to misinterpretation of spoken words
Solution Approach 1:
The system analyzes the pronunciation rate of correction queries and uses this feedback to identify which word in the original query should be replaced. The pronunciation rate serves as feedback information that helps the system distinguish between intentional corrections and normal speech variations, thereby improving word recognition accuracy.
Solution Approach 2:
The system changes the parameter being measured from simple voice recognition to voice recognition combined with pronunciation rate analysis. By introducing pronunciation rate as an additional parameter, the system can more accurately identify misinterpreted words and generate corrected queries, thus improving measurement precision while maintaining ease of operation.
2Reliability
If the user repeats the entire voice query to correct misinterpretation, then the reliability of the query is improved, but the loss of time increases
Solution Approach 1:
The system extracts only the misinterpreted word from the original query based on pronunciation rate analysis, rather than requiring the user to repeat the entire query. By taking out only the problematic word and replacing it with the correct word, the system maintains query reliability while significantly reducing the time loss for correction.
Solution Approach 2:
The system segments the correction process into identifying the specific misinterpreted word through pronunciation rate analysis and then replacing only that word. This segmentation allows the system to maintain high reliability by precisely targeting the error while minimizing the time required for correction compared to repeating the entire query.
3Measurement precision
If the system analyzes pronunciation rate to identify correction words, then the measurement precision is improved, but the device complexity increases
Solution Approach 1:
The system introduces pronunciation rate as an additional analysis parameter to improve measurement precision in identifying correction words. While this increases device complexity by requiring pronunciation rate calculation and comparison, the complexity is justified by the significant improvement in accurately identifying which word needs correction.
Data Source
AI summary
Systems and methods for correcting a voice query based on a subsequent voice query with a lower pronunciation rate. In some aspects, the systems and methods calculate first and second pronunciation rates of first and second voice queries. The systems and methods determine that the second pronunciation rate is lower than the first pronunciation rate and determine a first candidate pronunciation time for a first candidate word from the first voice query. The systems and methods determine a second candidate pronunciation time, adjusted to the first pronunciation rate, for the second candidate word from the second voice query. The systems and methods determine that the first candidate pronunciation time matches the second candidate pronunciation time and generate a third voice query based on the first voice query by replacing the first candidate word with the second candidate word.