Objective measures for predicting speech intelligibility in noisy conditions based on new band-importance functions

TLDR

The articulation index, speech‑transmission index, and coherence‑based intelligibility metrics have mainly been tested in steady‑state noise and not extensively in fluctuating noise conditions. The study aims to evaluate new speech‑based STI measures, modified coherence‑based measures, and AI‑based measures operating on short‑term (30 ms) intervals in realistic noisy conditions. The authors designed new band‑importance weighting functions for fluctuating maskers and evaluated the resulting measures using normal‑hearing listeners across 72 noisy conditions with four maskers. Modified coherence‑based and speech‑based STI measures incorporating signal‑specific band‑importance functions achieved the highest correlations (r = 0.89–0.94), with the coherence measure emphasizing vowel/consonant transitions reaching r = 0.94, indicating that traditional AI and STI indices could be improved by these functions.

Abstract

The articulation index (AI), speech-transmission index (STI), and coherence-based intelligibility metrics have been evaluated primarily in steady-state noisy conditions and have not been tested extensively in fluctuating noise conditions. The aim of the present work is to evaluate the performance of new speech-based STI measures, modified coherence-based measures, and AI-based measures operating on short-term (30ms) intervals in realistic noisy conditions. Much emphasis is placed on the design of new band-importance weighting functions which can be used in situations wherein speech is corrupted by fluctuating maskers. The proposed measures were evaluated with intelligibility scores obtained by normal-hearing listeners in 72 noisy conditions involving noise-suppressed speech (consonants and sentences) corrupted by four different maskers (car, babble, train, and street interferences). Of all the measures considered, the modified coherence-based measures and speech-based STI measures incorporating signal-specific band-importance functions yielded the highest correlations (r=0.89–0.94). The modified coherence measure, in particular, that only included vowel/consonant transitions and weak consonant information yielded the highest correlation (r=0.94) with sentence recognition scores. The results from this study clearly suggest that the traditional AI and STI indices could benefit from the use of the proposed signal- and segment-dependent band-importance functions.