Research
Loud and Clear: Dynamic Activation Steering for Improving Speech Intelligibility in Noisy Environments
arXiv:2610.07647v1 Announce Type: cross Abstract: Speech becomes less intelligible in noisy environments, and humans naturally adapt their voice to compensate. Inspired by this behavior, we investigat
arXiv:2610.07647v1 Announce Type: cross Abstract: Speech becomes less intelligible in noisy environments, and humans naturally adapt their voice to compensate. Inspired by this behavior, we investigate whether a text-to-speech (TTS) model can be guided to produce more intelligible speech using activation steering, without retraining. We focus on two characteristics of the Lombard effect: increased vocal effort and hyper-articulation. We introduce a prompt-relative steering mechanism that prevents steering effects from accumulating during generation while allowing their strength to be adjusted dynamically. Across seen and unseen speakers and multiple languages, our method produces systematic changes in Lombard-related acoustic features, preserves speaker similarity (89-95%), and reduces WER under background noise by 7-22% at 1 dB SNR. These results show that pretrained TTS models can be dynamically controlled to generate more intelligible speech without retraining.
Related
- Zero-Shot Lombard Speech Synthesis with Controllable Style Embeddings
- EmoRES-TTS: Residual-Enhanced Vector Steering for Emotional Speech Generation
- AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models
- NOPE-HYPE: A Structured Simulation Workflow for Robust Speech-to-Text Across Diverse Acoustic Environments
Source: arXiv cs.CL | 2026-10-07