Advancing Hearing Assessment: An ASR-Based Frequency-Specific Speech Test for Diagnosing Presbycusis

2025-05-28

AI Summary

Conventional audiometric tests inadequately quantify the functional impact of suprathreshold hearing loss—such as presbycusis—on speech understanding, particularly lacking objective, frequency-specific measures of perceptual deficits. Method: We propose a novel, frequency-specific speech test grounded in automatic speech recognition (ASR). By applying controlled acoustic degradation to simulate high-frequency hearing loss and leveraging ASR as an interpretable perceptual surrogate, our method analyzes phoneme-level confusion patterns—e.g., systematic substitutions (alveolar/palatal → labiodental) and deletions—to yield functional, frequency-resolved diagnostic insights beyond pure-tone audiometry. Contribution/Results: The constructed test corpus robustly discriminates normal-hearing from hearing-impaired listeners in simulation and successfully recapitulates hallmark perceptual deficits of presbycusis. This framework establishes a new paradigm for objective, fine-grained clinical hearing assessment.

Technology Category

• Natural Language Processing: Speech
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Security and Privacy: Large-scale security measurements

Abstract

Traditional audiometry often fails to fully characterize the functional impact of hearing loss on speech understanding, particularly supra-threshold deficits and frequency-specific perception challenges in conditions like presbycusis. This paper presents the development and simulated evaluation of a novel Automatic Speech Recognition (ASR)-based frequency-specific speech test designed to provide granular diagnostic insights. Our approach leverages ASR to simulate the perceptual effects of moderate sloping hearing loss by processing speech stimuli under controlled acoustic degradation and subsequently analyzing phoneme-level confusion patterns. Key findings indicate that simulated hearing loss introduces specific phoneme confusions, predominantly affecting high-frequency consonants (e.g., alveolar/palatal to labiodental substitutions) and leading to significant phoneme deletions, consistent with the acoustic cues degraded in presbycusis. A test battery curated from these ASR-derived confusions demonstrated diagnostic value, effectively differentiating between simulated normal-hearing and hearing-impaired listeners in a comprehensive simulation. This ASR-driven methodology offers a promising avenue for developing objective, granular, and frequency-specific hearing assessment tools that complement traditional audiometry. Future work will focus on validating these findings with human participants and exploring the integration of advanced AI models for enhanced diagnostic precision.

Problem

• Develops ASR-based test for frequency-specific speech deficits in presbycusis
• Analyzes phoneme-level confusion patterns to diagnose hearing loss
• Aims to complement traditional audiometry with objective granular assessment

Innovation

• ASR-based frequency-specific speech test
• Simulates hearing loss via acoustic degradation
• Analyzes phoneme-level confusion patterns