Outputs

Publications

Hughes, V., Llamas, C. and Kettig, T. (2022) Eliciting and evaluating likelihood ratios for speaker recognition by human listeners under forensically realistic channel-mismatched conditions. Proceedings of Interspeech. Incheon, Korea.

Invited talks

Hughes, V. (2022) Speaker recognition by humans and machines: some findings from a game-like elicitation task. UCL Speech Science Forum. 1 December 2022.

Hughes, V. (2022) Assessing the speaker recognition performance of humans and machines: implications for forensic voice comparison. LITHME Cost Action, Working Group 8 (Language Variation in the Human-Machine Era). 6 May 2022.

Presentations

Hughes, V., Llamas, C. and Kettig, T. (2022) Legal context biases listeners toward hearing voice pairs as more similar. New Ways of Analyzing Variation 50, San Jose, USA. 14 October 2022. (slides)

Hughes, V., Llamas, C. and Kettig, T. (2022) Eliciting and evaluating likelihood ratios for speaker recognition by human listeners under forensically realistic channel-mismatched conditions. Interspeech, Incheon, South Korea. 18-22 September 2022.

Hughes, V., Llamas, C., Kettig, T., Cutting, J. and Slawson, D. (2022). SoundJury: gamification of a speaker recognition experiment. Digital Creativity, Industry and Culture (DCIC) Conference, York, UK. 20 September 2022.

Hughes, V., Llamas, C. and Kettig, T. (2022) A game-based approach to eliciting and evaluating likelihood ratios for speaker recognition. International Association for Forensic Phonetics and Acoustics (IAFPA) Conference, Prague, Czechia. 10-13 July 2022.