Join us at Interspeech for events and drinks
Many InDeep researchers will be present at the Interspeech conference in Rotterdam, one of the largest and most prominent conferences on speech and speech technology world-wide. Therefore, we will be organizing a social event including drinks and snacks on Sunday 17 August at 19.00 in the Stuurboord bar at the Foodhallen Rotterdam. Stop by if you are also attending Interspeech! You don’t need to be registered for Interspeech to attend this social event – just fill in this form so we can estimate the number of guests.
InDeep at Interspeech
We’re excited to be contributing to Interspeech with the following events:
Sunday 17 August
– Speech Science Festival 10.00-17.30. InDeep provides a demonstration of emotion-decoding and removal. There are many other demonstrations for a broad audience. No registration for Interspeech is required for this festival.
– Tutorial, 15.30-18.30: InDeep members organize the tutorial Interpretability Techniques for Speech Model. Registration for Interspeech including for this tutorial is required.
– InDeep Social, 19.00: InDeep invites you to a drink and snacks in the Stuurboord bar at the Foodhallen. We will provide drinks and snacks. It is also possible to buy food at this venue at a number of different food stands. No registration for Interspeech required, but let us know by filling in this form.
Monday 18 August
– Special Session on Interpretability in Audio and Speech Technology, 11:00-13:00 (schedule is still subject to changes). Registration Interspeech required. Session with three papers by InDeep authors:
+ On the reliability of feature attribution methods for speech classification.
+ Word stress in self-supervised speech models: A cross-linguistic comparison.
+ What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training.
Consortium Meeting Groningen
On Friday September 20th InDeep met in the Groningen House of Connections for the next Consortium Meeting. In the morning RUG researchers Daniel Herrman (Philosophy of AI) and Yevgen Matusevych (Cognitive Plausibility of Modern LMs) gave illuminating talks on standards for belief representations in LLMs and bias in visually grounded speech models.
In the afternoon highlights from the various InDeep academic partners were shared, there was a poster session by researchers on their latest research results, as well as fruitful discussions on the future of interpretability methods in language, speech and music models and future directions of the InDeep project.
Consortium Meeting Amsterdam
On Friday March 8th InDeep had a Consortium meeting in the Amsterdam University Library. It was a day with both talks on recent progress in research, a tutorial, and lots of opportunity to discuss the strengths and weaknesses of interpretability techniques in text, translation, speech and music.
InDeep Masterclass: Explaining Foundation Models
On Thursday 2 November 2023, InDeep organized a Masterclass on Explaining Foundation Models. The event featured some inspiring talks, hands-on experience with explainability techniques for Large Language Models, and the opportunity to share insights and experiences. After the Masterclass there was a Meetup organized by Indeep and Amsterdam Al, on Alternatives for ChatGPT: How good are open source and in-house LLMs? To learn more about this event, you can download here an overview of the presentations and slides.