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

Abstract

Humans tend to speak louder and clearer in challenging environments, such as noisy conditions or when addressing hearing-impaired 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 clarity-related acoustic features. Furthermore, speech-in-noise experiments demonstrate that our model successfully simulates the intelligibility gains of human clear speech in noisy conditions.