# Synthesizing the Lombard Effect: Multi-Level Control of Speech Clarity and Vocal Effort in TTS

arXiv: https://arxiv.org/abs/2606.23176 · HTML: https://mlsanity.com/paper/2606.23176/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 22 Jun 2026.

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

- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [Matcha-TTS: A fast TTS architecture with conditional flow matching](https://mlsanity.com/paper/2309.03199/) (2023)
- [EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis](https://mlsanity.com/paper/2308.05725/) (2023)
- [Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion](https://mlsanity.com/paper/2008.05809/) (2020)
- [Whispered and Lombard Neural Speech Synthesis](https://mlsanity.com/paper/2101.05313/) (2021)
- [BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition](https://mlsanity.com/paper/2505.00059/) (2025)
- [Vocal effort modeling in neural TTS for improving the intelligibility of synthetic speech in noise](https://mlsanity.com/paper/2203.10637/) (2022)
- [Analysis and Synthesis of Hypo and Hyperarticulated Speech](https://mlsanity.com/paper/2006.04136/) (2020)
- [Voice Conversion for Lombard Speaking Style with Implicit and Explicit Acoustic Feature Conditioning](https://mlsanity.com/paper/2507.09310/) (2025)

## Built on by (most cited first, 1 of 1)

- [Loud and Clear: Dynamic Activation Steering for Improving Speech Intelligibility in Noisy Environments](https://mlsanity.com/paper/2610.07647/) (2026)

## Abstract (arXiv)

Humans tend to speak louder and clearer in challenging environments, such as noisy conditions or when addressing hearingimpaired listeners, which is called Lombard effect. To simulate this behavior in speech synthesis systems, we introduce a flow-matching based text-to-speech (TTS) model trained with vocal effort and articulation pseudo-labels. The proposed model achieves continuous and disentangled control of vocal effort and articulation, while also enabling word-level emphasis for clarifying specific segments of an utterance. Experimental results show that these control mechanisms effectively improve clarityrelated acoustic features. Furthermore, speech-in-noise experiments demonstrate that our model successfully simulates the intelligibility gains of human clear speech in noisy conditions.