Voice Query Pronunciation Metadata for Search Disambiguation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional voice query systems often lose pronunciation details during the conversion from speech to text, leading to ambiguity in identifying intended search queries, especially when multiple pronunciations correspond to different meanings.
Innovation Solution
The system incorporates pronunciation information into the text query or metadata, using phonetic translations and contextual inputs like user history and trends to accurately retrieve search results, ensuring that pronunciation details are retained and utilized for precise matching.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech is converted to text using ASR module, then voice query processing is enabled, but pronunciation details are lost
Solution Approach 1:
The system performs preliminary action by capturing and storing pronunciation information (phonetic transcripts) at the moment of speech-to-text conversion, before the pronunciation data would be lost. The ASR module generates both text and phonetic representations simultaneously, preserving the pronunciation characteristics for later disambiguation steps.
Solution Approach 2:
The patent introduces phonetic transcripts as an intermediary element between the ASR text output and the final search query interpretation. This intermediary layer preserves pronunciation information that mediates between the spoken input and the intended meaning, allowing the system to resolve ambiguities that pure text cannot address.
2Device complexity
If text query is generated from speech, then search processing is simplified, but ambiguity in word meanings increases
Solution Approach 1:
The system adds another dimension to the search query processing by incorporating phonetic information alongside textual information. This multi-dimensional approach allows the system to disambiguate words with multiple meanings by comparing both text matches and phonetic matches against database entries, thereby improving reliability without significantly increasing complexity.
3Measurement precision
If pronunciation information is retained in text query, then search accuracy improves, but data processing complexity increases
Solution Approach 1:
The patent segments the query processing into distinct components: text transcription, phonetic transcription, and database matching. By separating these functions, the system can process each component independently and combine results, improving search accuracy through multi-criteria matching while managing complexity through modular processing stages.
Data Source
AI summary
The system identifies one or more entities or content items among a plurality of stored information. The system generates an audio file based on a first text string that represents the entity or content item. Based on the first text string and at least one speech criterion, the system generating, using a speech-to-text module a second text string based on the audio file. The system then compares the text strings and stores the second text string if it is not identical to the first text string. The system generates metadata that includes results from text-speech-text conversions to forecast possible misidentifications when responding to voice queries during search operations. The metadata includes alternative representations of the entity.