2 citations · 2 across the 5 of their papers we have counts for
6 papers
Noise-Robust Forced Alignment for Spontaneous Speech
Laurin Wagner, Mario Zusag
We show that forced aligners degrade on spontaneous, noisy real-world speech, and that fillers, laughter, and disfluencies corrupt word boundaries, impacting many downstream applic…
Content is What Remains: Invariant Speech Tokenization from Parallel Utterances
Laurin Wagner, Bernhard Thallinger, Miroslav Stankovic +1
Discrete speech tokenizers aim to disentangle semantic from acoustic information, yet targets from self-supervised learning (SSL) models like HuBERT retain non-linguistic variation…
Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
Laurin Wagner, Mario Zusag, Bernhard Thallinger
Modern ASR models trained on heterogeneously annotated data treat transcription style (verbatim vs. intended) as an uncontrolled latent variable, causing measurable decoding instab…
CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions
Laurin Wagner, Bernhard Thallinger, Mario Zusag
We demonstrate that carefully adjusting the tokenizer of the Whisper speech recognition model significantly improves the precision of word-level timestamps when applying dynamic ti…
Careful Whisper -- leveraging advances in automatic speech recognition for robust and interpretable aphasia subtype classification
Laurin Wagner, Mario Zusag, Theresa Bloder
This paper presents a fully automated approach for identifying speech anomalies from voice recordings to aid in the assessment of speech impairments. By combining Connectionist Tem…
The Group Loss++: A deeper look into group loss for deep metric learning
Ismail Elezi, Jenny Seidenschwarz, Laurin Wagner +4
Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings…