On 2nd October 2024, the Language Technology Highlights 2024 (LT@FBK2024) event took place at Fondazione Bruno Kessler (FBK) in Povo, Italy. The event gathered a vibrant community of scientists, students, practitioners, and enthusiasts who shared the latest advancements in the field. Our ELOQUENCE Scientific Coordinator, Alessio Brutti, took a major role during the event, both in chairing the session and presenting the scientific paper.
A Day Full of Knowledge and Innovation
The event kicked off with Barbara Plank, keynote speaker, who set the tone for the day. Later on, the event was followed by a series of oral presentations featuring twelve papers accepted at top-tier language technology venues such as ACL and EMNLP. The event also included a session called “Building the LT Future: Insights from the LT@FBK Research Units”, where each of the core LT units at FBK had the opportunity to present their ongoing research activities. This session provided an in-depth look into the work being done at the research centre and offered valuable insights into the future progress of language technologies.
The ELOQUENCE project was also presented at the LT@FBK2024, with Alessio Brutti, the Scientific Coordinator at ELOQUENCE, chairing Session 1 on Language Technologies and Foundation Models. Alessio’s expertise in language technologies and foundation models made this session a key highlight of the event, with engaging discussions around the latest developments in these fields.
In addition to his role as chair, Alessio Brutti was also involved in the second session titled “Building the LT Future: Insights from the LT@FBK Research Units”, where he presented on Audio-visual Speech Recognition with Large Language Models (LLMs). Alessio represented the SpeechTek Lab at FBK, which is renowned for its work in AI-based speech technologies.
SpeechTek Lab: Innovating Speech Technologies
The SpeechTek Lab at FBK is at the forefront of AI-driven speech technologies, tackling a wide range of challenges in the speech domain, such as automatic speech recognition (ASR), speech enhancement, separation, spoken language understanding, and speaker identification. The lab is particularly focused on applying the latest AI research, including continual learning, large-scale models, self-supervised adaptation, and edge processing, to the speech context.
As we continue to advance in the development of smarter, more accurate systems, events like LT@FBK2024 will present fertile ground for expanding the language technology landscape.