Conversation Situation Extraction Using Specific Expression Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for analyzing conversations fail to accurately and efficiently extract specific situations, such as complaint responses or product purchases, from voice data in call center interactions, as they require comprehensive voice recognition and struggle with mixed speaker voices.
Innovation Solution
A system and method that includes a voice acquisition unit, a specific expression detection unit, and a specific situation extraction unit to identify and extract speech patterns from voice data, using keyword spotting and external characteristics like speech time and power, without needing full voice recognition, to determine specific situations like complaint responses or purchases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If comprehensive voice recognition is used to extract specific situations from conversations, then extraction accuracy may be improved, but system complexity and processing time increase significantly
Solution Approach 1:
The system segments the conversation analysis task into distinct components: voice activity detection (VAD) separates speech from non-speech, speaker identification distinguishes different speakers, and specific expression detection identifies target situations. This segmentation allows each component to be optimized independently, reducing overall system complexity while maintaining extraction accuracy.
Solution Approach 2:
The system extracts only the necessary features for specific situation detection rather than performing full voice recognition. By taking out and focusing on specific expressions and speech patterns relevant to the target situations, the system achieves accurate extraction without the computational burden of comprehensive voice recognition.
2Measurement precision
If full voice recognition is implemented to handle mixed speaker voices, then situation detection accuracy improves, but processing efficiency decreases
Solution Approach 1:
The system performs partial voice recognition by focusing only on detecting specific expressions and speech patterns rather than transcribing and understanding the entire conversation. This partial action approach maintains situation detection accuracy while significantly improving processing efficiency by avoiding unnecessary computational steps.
3Productivity
If keyword spotting and speech pattern analysis are used instead of full voice recognition, then processing speed improves, but the ability to handle noisy and multi-speaker environments may deteriorate
Solution Approach 1:
The system performs preliminary voice activity detection and speaker identification before specific expression detection. This preliminary action separates the mixed speaker voices and identifies speech segments, creating a cleaner input for the keyword spotting and speech pattern analysis. This preprocessing step ensures extraction reliability is maintained even in noisy and multi-speaker environments while preserving processing speed benefits.
Data Source
AI summary
A system, method, and computer readable article of manufacture for extracting a specific situation in a conversation. The system includes: an acquisition unit for acquiring speech voice data of speakers in the conversation; a specific expression detection unit for detecting the speech voice data of a specific expression from speech voice data of a specific speaker in the conversation; and a specific situation extraction unit for extracting, from the speech voice data of the speakers in the conversation, a portion of the speech voice data that forms a speech pattern that includes the speech voice data of the specific expression detected by the specific expression detection unit.