arXiv · 2611.19260
Auditory-Feedback-Conditioned Flow TTS for Implicit Lombard Adaptation
Abstract
Conventional text-to-speech (TTS) systems can lose intelligibility in noise environments because they cannot adapt to environmental changes. However, humans tend to increase their vocal efforts in noisy environments, a phenomenon known as the Lombard effect. Building on an auditory-feedback Lombard TTS, we investigate whether a pretrained Flow-based TTS can learn acoustic adaptation directly from auditory feedback without explicit prosodic control. Signal-to-noise ratio (SNR) feedback and automatic speech recognition (ASR) feedback are extracted from the noise-corrupted waveforms and injected into the Flow-matching condition for utterance refinement and causal block-level updates. We assess feedback benefits across prompting and noise conditions using plain/Lombard prompting, prompt-switching controls, and paired-finetuning. Experiments show that while finetuning provides strong robustness under in-domain conditions, auditory feedback yields additional cue-dependent benefits that generalize to unseen noise. Moreover, stronger power/F0 tracking alone does not guarantee better speech intelligibility or quality.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Yunya Wang, Satoshi Nakamura. 2026-11-14. Auditory-Feedback-Conditioned Flow TTS for Implicit Lombard Adaptation. https://searcharxiv.com/abs/2611.19260
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.