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

arXiv: https://arxiv.org/abs/2506.23367 · HTML: https://mlsanity.com/paper/2506.23367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 33 references that are in the map.
- First posted on arXiv 29 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)
- [Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search](https://mlsanity.com/paper/2005.11129/) (2020)
- [Matcha-TTS: A fast TTS architecture with conditional flow matching](https://mlsanity.com/paper/2309.03199/) (2023)
- [Leveraging Phone Mask Training for Phonetic-Reduction-Robust E2E Uyghur Speech Recognition](https://mlsanity.com/paper/2204.00819/) (2022)
- [Controllable Emphasis with zero data for text-to-speech](https://mlsanity.com/paper/2307.07062/) (2023)
- [A Systematic Review of Ethical Concerns with Voice Assistants](https://mlsanity.com/paper/2211.04193/) (2022)
- [Mmm whatcha say? Uncovering distal and proximal context effects in first and second-language word perception using psychophysical reverse correlation](https://mlsanity.com/paper/2406.05515/) (2024)
- [I Know You're Listening: Adaptive Voice for HRI](https://mlsanity.com/paper/2506.15107/) (2025)

## Abstract (arXiv)

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.