Sentiment Detection via Glottal Closure and Harmonic Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods fail to accurately detect sentiment from human speech, limiting organizations' ability to infer customer satisfaction and escalate conversations effectively.
Innovation Solution
A method and system that analyze human speech by determining time instances of glottal closure, generating a voice source signal, calculating relative harmonic strengths, and creating feature vectors to detect sentiment, utilizing processors to identify deviations in harmonics from the fundamental frequency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional sentiment detection methods are used, then the system is simple to implement, but the measurement precision of sentiment detection is insufficient
Solution Approach 1:
The speech signal analysis is segmented into multiple processing stages: voice source signal generation from glottal closure instances, harmonic contour extraction, relative harmonic strength calculation, and feature vector construction. Each stage processes specific aspects of the speech signal separately, improving sentiment detection precision while managing system complexity through modular processing
Solution Approach 2:
The patent transforms the speech signal from time-domain representation to frequency-domain analysis by examining harmonic contours and relative harmonic strengths across multiple frequency dimensions. This dimensional transformation enables more accurate sentiment detection by capturing spectral characteristics that are not apparent in the time domain
2Measurement precision
If detailed speech signal analysis is performed, then sentiment detection accuracy improves, but the processing time increases
Solution Approach 1:
The patent extracts only the most relevant features from the speech signal for sentiment detection: glottal closure time instances, harmonic contours, and relative harmonic strengths. By extracting specifically these features rather than processing the entire speech signal in detail, the system achieves accurate sentiment detection while reducing overall processing time
Solution Approach 2:
The analysis focuses on partial aspects of the speech signal that are most indicative of sentiment - specifically the harmonic structure and glottal closure patterns - rather than performing exhaustive analysis of all speech signal characteristics. This partial action approach maintains detection accuracy while reducing processing time
Data Source
AI summary
A method and a system for detecting sentiment of a human based on an analysis of human speech are disclosed. In an embodiment, one or more time instances of glottal closure are determined from a speech signal of the human. A voice source signal based on the determined one or more time instances of glottal closure is generated. A set of relative harmonic strengths is determined based on one or more harmonic contours of the voice source signal. The RHS is indicative of a deviation of the one or more harmonics of the voice source signal from a fundamental frequency of the voice source signal. A set of feature vectors is determined based on the RHS. The set of feature vectors are utilizable to detect the sentiment of the human.