Synthesizing the Lombard Effect: Multi-Level Control of Speech Clarity and Vocal Effort in TTS
A text-to-speech model is trained to simulate the Lombard effect, improving clarity in noisy conditions.
The paper introduces a new approach to simulate the Lombard effect in speech synthesis systems, which is not previously explored in prior work.
Before reading this…
Applications
- →Speech synthesis in noisy environments
- →Communication with hearing-impaired individuals
To understand this paper, make sure you know these concepts first:
- Text-to-speech systemsfind papers →
- Speech synthesis techniquesfind papers →
Abstract
More Like ThisHumans 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.