Room number

IDEG110

Telephone number

• office: +43 316 873 - 4485

Position

Research Associate

Email

wepner@tugraz.at

Other Profiles

• TUGRAZonline

Saskia Wepner received her Master’s degree in Electrical Engineering, Information Technology and Computer Engineering from RWTH Aachen University, Germany. As part of the Medical Acoustics group of the Institute of Technical Acoustics (today: Institute for Hearing Technology and Acoustics, RWTH), she specialised in psychoacoustics. In her PhD studies at TU Graz, she has been focussing on human and automatic speech recognition of spontaneous, unscripted conversations, and on prosodic patterns in turn-taking. Her research has always been based on interdisciplinary projects, joining her technical background with other disciplines, such as psychology and linguistics.

---

Research Projects

• Cross-layer language models for conversational speech (FWF Stand-Alone Project P 32700-N)

Student Projects

• How fillers affect human transcription accuracy of disfluent utterances in conversational speech
• Classification of Communicative Functions(open)
• Comparison of Automatic and Human Speech Recognition
• Machine Learning for Automatic F0 Contour Discrimination and Labelling
• Automatic Labelling of Creaky Patterns in Speech Signals
• Detection and visualisation of F0 tracking errors

PhD Thesis

• (When) Does it Harm to Be Incomplete? Comparing Human and Automatic Speech Recognition of Syntactically Disfluent Utterances

Publications

• Conference paper Eckert L., Wepner S. & Schuppler B. (2025) Slicer – A Tool for Efficient Stimuli Extraction from Large Speech Corpora. in Forum Acusticum Euronoise 2025. [more info]
• Journal article Wepner S., Lennkh S., Winkler J., Kubin G. & Schuppler B. (2024) (When) Does it harm to be incomplete? Human and automatic speech recognition of syntactically disfluent structures. in Speech Communication. [more info]
• Preprint Linke J., Wepner S., Kubin G. & Schuppler B. (2023) Using Kaldi for Automatic Speech Recognition of Conversational Austrian German.. [more info] [doi]
• Conference paper Kelterer A., Wepner S., Linke J. & Schuppler B. (2023) Points of maximum grammatical control – The prosody of a turn-holding practice. in 20th International Congress on Phonetic Sciences (pp. 3467-3471). [more info]
• Conference paper Paierl M., Röck T., Wepner S., Kelterer A. & Schuppler B. (2023) Creapy: A Python-based tool for the detection of creak in conversational speech. in 20th International Congress on Phonetic Sciences (pp. 1716). [more info]
• Conference paper Kelterer A., Wepner S., Christian S., Schuppler B. & Zarka D. (2022) Prosodic cues to agreement and disagreement prefaces in Austrian German conversations. in 1st International Conference on Tone and Intonation (pp. 107-111). [more info] [doi]
• Conference paper Wepner S., Schuppler B. & Kubin G. (2022) How prosody affects ASR performance in conversational Austrian German. in Speech Prosody 2022 (pp. 195-199). [more info] [doi]
• Abstract Kelterer A., Christian S., Wepner S., Linke J. & Zarka D. (2021) Prosodic cues to agreement and disagreement in "ja" and "nein" prefaces in Austrian German conversations.. [more info]
• Abstract Wepner S. (2021) Adaptation of Automatic Speech Recognition systems to the needs of Austrian German.. [more info]