Roman Böhringer

According to our database, Roman Böhringer authored at least 7 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Demonstration of Adapt4Me: An Uncertainty-Aware Authoring Environment for Personalizing Automatic Speech Recognition to Non-normative Speech.

Niclas Pokel, Yiming Zhao, Pehuen Moure, Yingqiang Gao, Roman Böhringer

CoRR, March, 2026

2025

Variational Low-Rank Adaptation for Personalized Impaired Speech Recognition.

Niclas Pokel, Pehuen Moure, Roman Böhringer, Shih-Chii Liu, Yingqiang Gao

CoRR, September, 2025

Data-Efficient ASR Personalization for Non-Normative Speech Using an Uncertainty-Based Phoneme Difficulty Score for Guided Sampling.

Niclas Pokel, Pehuen Moure, Roman Böhringer, Yingqiang Gao

CoRR, September, 2025

Adapting Foundation Speech Recognition Models to Impaired Speech: A Semantic Re-chaining Approach for Personalization of German Speech.

Niclas Pokel, Pehuen Moure, Roman Böhringer, Yingqiang Gao

CoRR, June, 2025

2024

Process-as-a-Service: Unifying Elastic and Stateful Clouds with Serverless Processes.

Marcin Copik, Alexandru Calotoiu, Gyorgy Réthy, Roman Böhringer, Rodrigo Bruno, Torsten Hoefler

Proceedings of the 2024 ACM Symposium on Cloud Computing, 2024

2023

FMI: Fast and Cheap Message Passing for Serverless Functions.

Marcin Copik, Roman Böhringer, Alexandru Calotoiu, Torsten Hoefler

Proceedings of the 37th International Conference on Supercomputing, 2023

2021

Clairvoyant prefetching for distributed machine learning I/O.

Nikoli Dryden, Roman Böhringer, Tal Ben-Nun, Torsten Hoefler

Proceedings of the International Conference for High Performance Computing, 2021