Dominik Wagner

According to our database, Dominik Wagner authored at least 31 papers between 2019 and 2025.

Collaborative distances:

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

2025

Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition.

Dominik Wagner, Ilja Baumann, Natalie Engert, Seanie Lee, Elmar Nöth, Korbinian Riedhammer, Tobias Bocklet

CoRR, May, 2025

FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA.

Seanie Lee, Sangwoo Park, Dong Bok Lee, Dominik Wagner, Haebin Seong, Tobias Bocklet, Juho Lee, Sung Ju Hwang

CoRR, May, 2025

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models.

Seanie Lee, Haebin Seong, Dong Bok Lee, Minki Kang, Xiaoyin Chen, Dominik Wagner, Yoshua Bengio, Juho Lee, Sung Ju Hwang

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Optimized Self-supervised Training with BEST-RQ for Speech Recognition.

Ilja Baumann, Dominik Wagner, Korbinian Riedhammer, Tobias Bocklet

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions.

Dominik Wagner, Alexander W. Churchill, Siddharth Sigtia, Erik Marchi

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models.

Seanie Lee, Dong Bok Lee, Dominik Wagner, Minki Kang, Haebin Seong, Tobias Bocklet, Juho Lee, Sung Ju Hwang

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

Generative adversarial networks for whispered to voiced speech conversion: a comparative study.

Dominik Wagner, Ilja Baumann, Tobias Bocklet

Int. J. Speech Technol., December, 2024

Personalizing Large Sequence-to-Sequence Speech Foundation Models With Speaker Representations.

Dominik Wagner, Ilja Baumann, Thomas Ranzenberger, Korbinian Riedhammer, Tobias Bocklet

Proceedings of the IEEE Spoken Language Technology Workshop, 2024

Automatic Evaluation of a Sentence Memory Test for Preschool Children.

Ilja Baumann, Nicole Unger, Dominik Wagner, Korbinian Riedhammer, Tobias Bocklet

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Towards Self-Attention Understanding for Automatic Articulatory Processes Analysis in Cleft Lip and Palate Speech.

Ilja Baumann, Dominik Wagner, Maria Schuster, Korbinian Riedhammer, Elmar Nöth, Tobias Bocklet

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models.

Dominik Wagner, Ilja Baumann, Korbinian Riedhammer, Tobias Bocklet

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Large Language Models for Dysfluency Detection in Stuttered Speech.

Dominik Wagner, Sebastian P. Bayerl, Ilja Baumann, Elmar Nöth, Korbinian Riedhammer, Tobias Bocklet

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

A Multimodal Approach to Device-Directed Speech Detection with Large Language Models.

Dominik Wagner, Alexander W. Churchill, Siddharth Sigtia, Panayiotis G. Georgiou, Matt Mirsamadi, Aarshee Mishra, Erik Marchi

Proceedings of the IEEE International Conference on Acoustics, 2024

Towards Interpretability of Automatic Phoneme Analysis in Cleft Lip and Palate Speech.

Ilja Baumann, Dominik Wagner, Maria Schuster, Elmar Nöth, Tobias Bocklet

Proceedings of the IEEE International Conference on Acoustics, 2024

MMUTF: Multimodal Multimedia Event Argument Extraction with Unified Template Filling.

Philipp Seeberger, Dominik Wagner, Korbinian Riedhammer

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Optimized Speculative Sampling for GPU Hardware Accelerators.

Dominik Wagner, Seanie Lee, Ilja Baumann, Philipp Seeberger, Korbinian Riedhammer, Tobias Bocklet

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023

Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models.

Dominik Wagner, Alexander W. Churchill, Siddharth Sigtia, Panayiotis G. Georgiou, Matt Mirsamadi, Aarshee Mishra, Erik Marchi

CoRR, 2023

Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks.

Dominik Wagner, Ilja Baumann, Tobias Bocklet

CoRR, 2023

Multi-class Detection of Pathological Speech with Latent Features: How does it perform on unseen data?

Dominik Wagner, Ilja Baumann, Franziska Braun, Sebastian P. Bayerl, Elmar Nöth, Korbinian Riedhammer, Tobias Bocklet

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

A Stutter Seldom Comes Alone - Cross-Corpus Stuttering Detection as a Multi-label Problem.

Sebastian P. Bayerl, Dominik Wagner, Ilja Baumann, Florian Hönig, Tobias Bocklet, Elmar Nöth, Korbinian Riedhammer

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Influence of Utterance and Speaker Characteristics on the Classification of Children with Cleft Lip and Palate.

Ilja Baumann, Dominik Wagner, Franziska Braun, Sebastian P. Bayerl, Elmar Nöth, Korbinian Riedhammer, Tobias Bocklet

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Speaker Adaptation for End-to-End Speech Recognition Systems in Noisy Environments.

Dominik Wagner, Ilja Baumann, Sebastian P. Bayerl, Korbinian Riedhammer, Tobias Bocklet

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

Detection of Vowel Errors in Children's Speech using Synthetic Phonetic Transcripts.

Ilja Baumann, Dominik Wagner, Korbinian Riedhammer, Elmar Nöth, Tobias Bocklet

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022

Dysfluencies Seldom Come Alone - Detection as a Multi-Label Problem.

Sebastian P. Bayerl, Dominik Wagner, Florian Hönig, Tobias Bocklet, Elmar Nöth, Korbinian Riedhammer

CoRR, 2022

The Importance of Speech Stimuli for Pathologic Speech Classification.

Ilja Baumann, Dominik Wagner, Franziska Braun, Sebastian P. Bayerl, Elmar Nöth, Korbinian Riedhammer, Tobias Bocklet

CoRR, 2022

Detecting Vocal Fatigue with Neural Embeddings.

Sebastian P. Bayerl, Dominik Wagner, Ilja Baumann, Korbinian Riedhammer, Tobias Bocklet

CoRR, 2022

The Influence of Dataset Partitioning on Dysfluency Detection Systems.

Sebastian P. Bayerl, Dominik Wagner, Elmar Nöth, Tobias Bocklet, Korbinian Riedhammer

Proceedings of the Text, Speech, and Dialogue - 25th International Conference, 2022

Generative Models for Improved Naturalness, Intelligibility, and Voicing of Whispered Speech.

Dominik Wagner, Sebastian P. Bayerl, Héctor A. Cordourier Maruri, Tobias Bocklet

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0.

Sebastian Peter Bayerl, Dominik Wagner, Elmar Nöth, Korbinian Riedhammer

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Nonwords Pronunciation Classification in Language Development Tests for Preschool Children.

Ilja Baumann, Dominik Wagner, Sebastian P. Bayerl, Tobias Bocklet

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

2019

Latent representations of transaction network graphs in continuous vector spaces as features for money laundering detection.

Dominik Wagner

Proceedings of the Studierendenkonferenz Informatik, 2019