Alexander Waibel

Automating clinical note generation from speech could drastically reduce healthcare workers' documentation time while preserving essential patient information.

High speech overlap isn't the primary challenge in cocktail-party scenarios; innovative audio-visual strategies and large language models can cut recognition errors by 57%.

Context biasing methods can slash biased word error rates by up to 88%, outperforming speech LLMs in challenging ASR scenarios.

Disfluencies are not just noise; they carry crucial meaning that, when ignored, significantly degrades translation quality.

Personalized fine-tuning of ASR models can reduce word error rates for dysarthric speech to as low as 9.7%, transforming communication for affected individuals.

Speech synthesis can now adaptively enhance clarity and vocal effort, mimicking human responses in noisy environments.

Text prompts might be inflating your SLLM's performance: spoken prompts reveal a significant performance gap, especially in low-resource languages.