Covertly improving intelligibility with data-driven adaptations of speech timing

2026-03-31

AI Summary

This study challenges the conventional assumption that uniformly slowing speech rate universally enhances intelligibility, particularly for listeners with hearing impairment or non-native speakers, for whom such global slowing often yields limited benefits. The authors identify a “scissors-like” temporal pattern in how speech rate affects intelligibility: critical phonetic segments—especially those carrying vowel contrasts—require localized slowing, while other segments can retain natural timing without compromising comprehension. Building on this insight, they propose the first data-driven algorithm for selective, local speech-rate modification, validated through reverse correlation experiments and cross-linguistic listener testing. Results demonstrate that this approach significantly improves word recognition accuracy under adverse conditions such as background noise across diverse listener groups, without perceptible alterations to speech rhythm. In contrast, uniform slowing not only fails to confer consistent benefits but can even increase comprehension errors.

Abstract

Human talkers often address listeners with language-comprehension challenges, such as hard-of-hearing or non-native adults, by globally slowing down their speech. However, it remains unclear whether this strategy actually makes speech more intelligible. Here, we take advantage of recent advancements in machine-generated speech allowing more precise control of speech rate in order to systematically examine how targeted speech-rate adjustments may improve comprehension. We first use reverse-correlation experiments to show that the temporal influence of speech rate prior to a target vowel contrast (ex. the tense-lax distinction) in fact manifests in a scissor-like pattern, with opposite effects in early versus late context windows; this pattern is remarkably stable both within individuals and across native L1-English listeners and L2-English listeners with French, Mandarin, and Japanese L1s. Second, we show that this speech rate structure not only facilitates L2 listeners' comprehension of the target vowel contrast, but that native listeners also rely on this pattern in challenging acoustic conditions. Finally, we build a data-driven text-to-speech algorithm that replicates this temporal structure on novel speech sequences. Across a variety of sentences and vowel contrasts, listeners remained unaware that such targeted slowing improved word comprehension. Strikingly, participants instead judged the common strategy of global slowing as clearer, even though it actually increased comprehension errors. Together, these results show that targeted adjustments to speech rate significantly aid intelligibility under challenging conditions, while often going unnoticed. More generally, this paper provides a data-driven methodology to improve the accessibility of machine-generated speech which can be extended to other aspects of speech comprehension and a wide variety of listeners and environments.

Problem

• speech intelligibility
• speech rate adaptation
• covert enhancement
• vowel contrast
• machine-generated speech

Innovation

• data-driven speech adaptation
• targeted speech-rate adjustment
• temporal structure of speech
• speech intelligibility
• machine-generated speech