2 citations · 2 across the 3 of their papers we have counts for
3 papers
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…