Speech Sample Alignment for Physiological State Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems lack effective methods for assessing the physiological state of a subject through speech analysis, particularly in identifying conditions such as congestive heart failure, coronary heart disease, atrial fibrillation, chronic obstructive pulmonary disease, asthma, interstitial lung disease, pulmonary edema, Parkinson's disease, bipolar disorder, and depression, by accurately mapping and comparing speech samples to determine deviations from a known physiological state.
Innovation Solution
A system and method that maps a test speech sample to a reference speech sample or a speech model, dividing the samples into segments based on acoustic properties, computes distances between these segments, and communicates an output indicating the physiological state based on predefined constraints and thresholds, using dynamic time warping or Hidden Markov Models to align and compare acoustic features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If speech samples are segmented and mapped using dynamic time warping or Hidden Markov Models, then measurement precision of physiological state assessment is improved, but device complexity increases
Solution Approach 1:
The speech sample is divided into multiple segments based on acoustic properties such as pitch, energy, and spectral features. This segmentation allows for more granular analysis of different portions of speech, enabling precise identification of physiological state indicators while using computationally efficient segment-level processing rather than analyzing the entire speech sample as a single complex unit.
Solution Approach 2:
Acoustic feature extraction serves as an intermediary step between raw speech signals and physiological state assessment. The system extracts intermediate acoustic features (pitch, energy, spectral characteristics) that mediate between the complex speech signal and the final physiological state determination, simplifying the overall analysis while maintaining precision.
2Measurement precision
If speech samples are divided into multiple segments based on acoustic properties, then measurement precision is improved, but loss of time increases
Solution Approach 1:
Acoustic feature extraction is performed preliminarily on each speech segment before detailed comparison and analysis. By pre-computing acoustic properties such as pitch contours, energy distribution, and spectral features for each segment, the system reduces the computational burden of subsequent matching operations, thereby decreasing overall processing time while maintaining segmentation benefits for precision.
3Reliability
If mapping is performed between test speech sample and reference speech sample, then reliability of physiological state assessment is improved, but device complexity increases
Solution Approach 1:
The system creates simplified acoustic representations (copies) of reference speech samples during a training phase, storing segmented acoustic features and physiological state labels. During assessment, the system compares test speech against these pre-processed references rather than performing complex real-time comparisons, thereby improving reliability through consistent reference matching while reducing operational complexity.
Data Source
AI summary
A method includes mapping, by a processor, a test speech sample, which was produced by a subject while a physiological state of the subject was unknown, to a reference speech sample, which was produced in a known physiological state. The method further includes, based on the mapping, computing a distance between the test speech sample and the reference speech sample, and in response to the distance, communicating an output indicating the physiological state of the subject while the test speech sample was produced. Other embodiments are also described.