Extended Phonetic Dictionary for Name Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Speech recognition systems face difficulties in recognizing names due to lack of modeling in phonetic dictionaries and variations in locale-specific pronunciations, leading to inaccurate recognition of names in contacts databases.
Innovation Solution
An extended phonetic dictionary is created by processing user database words using multiple pronunciation guessers for various locales, which can be updated dynamically, allowing for phonetic fuzzy matching to improve name recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a conventional phonetic dictionary is used for speech recognition, then the system structure remains simple and fast, but name recognition accuracy deteriorates because names are often not modeled in the dictionary or are in different locales
Solution Approach 1:
The system pre-processes words from the user's contacts database using pronunciation guessers to generate phonetic transcriptions before speech recognition occurs. This preliminary action creates an extended phonetic dictionary specific to the user's names and locales, improving recognition accuracy without requiring a complete redesign of the phonetic dictionary structure
Solution Approach 2:
Pronunciation guessers act as intermediaries between the conventional phonetic dictionary and user-specific names. These guessers generate phonetic transcriptions for names not found in the standard dictionary, bridging the gap between conventional phonetic modeling and diverse user names across different locales
2Adaptability or versatility
If the phonetic dictionary is updated dynamically at runtime based on user database changes, then name recognition adaptability improves, but system processing time and computational resources increase
Solution Approach 1:
The system updates the extended phonetic dictionary periodically or on-demand rather than continuously. When the contacts database changes, the system processes only the changed entries through pronunciation guessers and updates the extended dictionary accordingly, rather than reprocessing the entire database, thus reducing runtime overhead while maintaining adaptability
Solution Approach 2:
The phonetic dictionary system transitions from a static conventional dictionary to a dynamic extended dictionary that adapts to user-specific names and locales. The extended dictionary is built and updated dynamically based on user database contents, allowing the system to adapt to different users' naming conventions and pronunciations without requiring full reprocessing each time
Data Source
AI summary
A speech recognition system uses, in one embodiment, an extended phonetic dictionary that is obtained by processing words in a user's set of databases, such as a user's contacts database, with a set of pronunciation guessers. The speech recognition system can use a conventional phonetic dictionary and the extended phonetic dictionary to recognize speech inputs that are user requests to use the contacts database, for example, to make a phone call, etc. The extended phonetic dictionary can be updated in response to changes in the contacts database, and the set of pronunciation guessers can include pronunciation guessers for a plurality of locales, each locale having its own pronunciation guesser.