Harmonic Beamformers for Non-Intrusive Speech Intelligibility Prediction

Abstract

In recent years, research into objective speech intelligibility measures has gained increased interest as a tool to optimize speech enhancement algorithms. While most intelligibility measures are intrusive, i.e., they require a clean reference signal, this is rarely available in real-time applications. This paper proposes two non-intrusive intelligibility measures, which allow using the intrusive short-time objective intelligibility (STOI) measure without requiring access to the clean signal. Instead, a reference signal is obtained from the degraded signal using either a fixed or an adaptive harmonic spatial filter. This reference signal is then used as input to STOI. The experimental results show a high correlation between both proposed non-intrusive speech intelligibility measures and the original intrusively computed STOI scores.

An Exploratory Analysis of Air Traffic Controller Speech Intelligibility Using Voice Data from a Simulation Experiment

“…Communication is susceptible to distortion of systematic, environmental, and internal factors that affect its comprehensibility or speech intelligibility (SI). There is growing interest in research on devising objective and non-intrusive SI metrics in fields such as speech processing (Feng & Chen, 2022;Sørensen, Boldt, & Christensen, 2019). SI is measured as the average percentage of words or phonetic units (e.g., syllables) that the listener can recognize.…”