You Sound a Little Tense: L2 Tailored Clear TTS Using Durational Vowel Properties

TL;DR

This paper introduces a TTS system tailored for L2 speakers that uses vowel duration differences to improve clarity, reducing transcription errors without affecting perceived intelligibility.

Contribution

It presents a novel clarity mode leveraging durational vowel properties for L2 TTS, demonstrating improved intelligibility and revealing perceptual differences in speech understanding.

Findings

Fewer transcription errors with clarity mode (at least 9.15%)

Listeners preferred clarity mode over slowed speech

Whisper-ASR does not replicate L2 speaker cues

Abstract

We present the first text-to-speech (TTS) system tailored to second language (L2) speakers. We use duration differences between American English tense (longer) and lax (shorter) vowels to create a "clarity mode" for Matcha-TTS. Our perception studies showed that French-L1, English-L2 listeners had fewer (at least 9.15%) transcription errors when using our clarity mode, and found it more encouraging and respectful than overall slowed down speech. Remarkably, listeners were not aware of these effects: despite the decreased word error rate in clarity mode, listeners still believed that slowing all target words was the most intelligible, suggesting that actual intelligibility does not correlate with perceived intelligibility. Additionally, we found that Whisper-ASR did not use the same cues as L2 speakers to differentiate difficult vowels and is not sufficient to assess the intelligibility of TTS systems for these individuals.