Speaker Age Estimation via Formant Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current voice-activated and voice-controlled devices are unable to accurately estimate the age of a speaker based on their speech patterns.
Innovation Solution
A system comprising a microphone, analog-to-digital converter, and a computing device with an age estimation database and executable code that processes digitized speech to identify formant-based feature vectors, matching them with age-deterministic phonemes to estimate the speaker's age, using modules for speech segmentation, feature extraction, and age estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If voice-activated devices use basic speech recognition, then device complexity is low, but age estimation capability is insufficient
Solution Approach 1:
The system segments speech analysis into distinct modules: phoneme identification, formant extraction, and age estimation. Each module processes specific acoustic features independently, enabling accurate age estimation while maintaining manageable system complexity through modular architecture.
Solution Approach 2:
The system performs preliminary speech processing by extracting formant features and identifying phonemes before age estimation. This preliminary analysis prepares the data in advance, allowing the age estimation algorithm to work with pre-processed features rather than raw speech signals, improving accuracy without proportionally increasing complexity.
2Measurement precision
If the system processes all speech features, then age estimation accuracy improves, but processing time increases
Solution Approach 1:
The system extracts only the most relevant features for age estimation: formant frequencies and phoneme identities. By taking out and focusing on these specific acoustic features rather than processing all possible speech characteristics, the system achieves accurate age estimation with reduced processing time.
Solution Approach 2:
The system performs partial processing by analyzing only certain phonemes and their formant characteristics that are most indicative of age. This selective approach processes sufficient features to achieve accurate estimation without the computational burden of analyzing every aspect of the speech signal.
Data Source
AI summary
There is provided a system comprising a microphone, configured to receive an input speech from an individual, an analog-to-digital (A/D) converter to convert the input speech to digital form and generate a digitized speech, a memory storing an executable code and an age estimation database, a hardware processor executing the executable code to receive the digitized speech, identify a plurality of boundaries in the digitized speech delineating a plurality of phonemes in the digitized speech, extract a plurality of formant-based feature vectors from each phoneme in the digitized speech based on at least one of a formant position, a formant bandwidth, and a formant dispersion, compare the plurality of formant-based feature vectors with age determinant formant-based feature vectors of the age estimation database, determine the age of the individual when the comparison finds a match in the age estimation database, and communicate an age-appropriate response to the individual.