Biography
Linda Gerlach is a PhD candidate in Computation, Cognition and Language, supervised by Dr Kirsty McDougall. Her research focuses on the selection of similar speakers based on perceptual judgements and measured features for forensic applications. She completed her undergraduate degree in Language and Communication at Philips University Marburg (Germany), and obtained an MA degree in Speech Science with a focus on phonetics at the same university. Whilst on an internship at Oxford Wave Research and in collaboration with the phonetics laboratory of the University of Cambridge, she explored the perception of voice similarity based on listener ratings and output from an automatic speaker recognition system for her final MA project. During her MA degree, she also worked as a student assistant on Regionalsprache.de (REDE) projects at the Forschungszentrum Deutscher Sprachatlas, which investigates modern regional languages of German.
Research
- Forensic speech science
- Voice similarity
- Automatic speaker recognition
- Speech technology
- Speaker characteristics
Publications
Gerlach, L., McDougall, K., Kelly, F., Alexander, A., & Nolan, F. (2020). Exploring the relationship between voice similarity estimates by listeners and by an automatic speaker recognition system incorporating phonetic features. Speech Communication, 124, 85–95. https://doi.org/10.1016/j.specom.2020.08.003 [pre-print]
Gerlach, L., Coy, T., McDougall, K., Kelly, F., & Alexander, A. (2021). How does the perceptual similarity of the relevant population to a questioned speaker affect the likelihood ratio?, IAFPA conference proceedings 2021, Marburg/Germany (online).
Gerlach, L., McDougall, K., Kelly, F., & Alexander, A. (2021). How do automatic speaker recognition systems ‘perceive’ voice similarity? Further exploration of the relationship between human and machine voice similarity ratings (presentation). IAFPA conference proceedings 2021, Marburg/Germany (online).
Gerlach, L., Kelly, F., & Alexander, A. (2019). More than just identity: speaker recognition and speaker profiling using the GBR-ENG database (poster). IAFPA conference proceedings 2019, Istanbul/Turkey. (Best student poster award)
Gerlach, L., Kelly, F., & Alexander, A. (2019). One out of many: A sliding window approach to automatic speaker recognition with multi-speaker files (presentation). IAFPA conference proceedings 2019, Istanbul/Turkey.
Teaching and Supervisions
2020-2022:
Li1 (Sounds and Words) Supervisions - Section of Theoretical and Applied Linguistics
Other Professional Activities
Research Scientist and QA Manager at Oxford Wave Research
