P&P 2024 (October 1-2, 2024)

The conference on phonetics and phonlogy in the German-speaking region (P&P) — Phonetik und Phonologie im deutschsprachigen Raum — was once again a fantastic opportunity to catch up with colleagues. The team around Sven Grawunder did a great job hosting the meeting at Martin Luther University Halle-Wittenberg in Halle/Saale, Germany. 🙌

I was delighted to present joint work with my former UCD Master’s student Jiaman He on The Influence of Visual Context on the Perception of Voice Assistant Gender. This work explores whether listeners perceive Apple Siri’s gender-neutral American English voice Quinn as neutral and if visual context influences this perception. 🔜 The full paper is to appear in the conference proceedings. 📒

Foto

BICLCE 2024 (September 26-28, 2024)

I was delighted to attend the Biennial International Conference on the Linguistics of Contemporary English (BICLCE) 🚲 for the first time this year! The meeting was expertly hosted by the University of Alicante in the Valencian region of Spain.

I presented our work on querying the embeddings of automatic speech recognition (ASR) for phonetic information in the workshop on Corpus Phonology: Current Approaches and Future Directions which was organized by Philipp Meer and Ulrike Gut from the University of Münster in Germany.

Foto

Other topics of the workshop included down-sampling strategies in corpus phonology, the performance of the ASR model Whisper on sociolinguistic data sets, and work on different varieties of English (Australian, New Zealand, Nigerian, and Scottish Standard English).

Interspeech 2024 (September 1-5, 2024)

Two very different worlds collided at Interspeech this year: speech science and all-inclusive tourism. 😄 We had a very good time on Kos Island in Greece!

Foto

We presented recent work from the Berndsen Lab at University College Dublin:

I also had the pleasure of presenting joint work with with Bistra Andreeva (Saarland University, Germany) and Benjamin R. Cowan (University College Dublin, Ireland) on The Use of Modifiers and f0 in Remote Referential Communication with Human and Computer Partners.

YFRSW 2024

I am very happy to have contributed to another successful edition of the Young Female* Researchers in Speech Workshop (YFRSW). This year, the workshop was held on the beautiful Greek island of Kos. We had the pleasure of welcoming our participants at the 2nd Lyceum of Kos. 🇬🇷 🏝 ☀️

Foto

Organizing this event would not have been possible without my fantastic co-chairs Leda Sari (Meta AI, USA) and Georgia Maniati (Samsung Electronics / Innoetics, Greece), as well as all members of the organizing committee: Johannah O’Mahony (University of Edinburgh, UK), Sarah Ita Levitan (City University of New York, USA), Vered Silber-Varod (Tel Aviv University, Israel), Sarenne Wallbridge (University of Edinburgh, UK), Aria Minaidi (Google, Poland), Aaricia Herygers (alphaspeech, Germany), Spyretta Leivaditi (University of Groningen, The Netherlands), and Yuanyuan Zhang (TU Delft, The Netherlands)! Thank you! 💕

*The workshop is open for marginalized genders, including women, as well as non-binary and gender non-conforming people who are comfortable in a space that is centered on women’s experiences in the speech science and technology community. We aim to offer an inclusive and accessible program.

New Paper! 🚨 VUI Partner Models of German and Japanese Users

Today, we presented our work on assessing partner models for voice user interfaces (VUIs) at the ACM Conference on Conversational User Interfaces in Luxembourg. If you work with German 🇩🇪 or Japanese 🇯🇵 speakers in spoken human-computer interaction and want to assess how competent and reliable, human-like, and flexible they perceive VUIs to be when communicating, please consider using our translated versions of the Partner Modelling Questionnaire!

Foto