Publications & Presentations
Scientific publications & Articles
Authors: Shashi Kumar, S Pavankumar Dubagunta, Iuliia Nigmatulina, Karthik Pandia, Esaú Villatoro-Tello, Srikanth Madikeri, Aravind Ganapathiraju & Petr Motlicek
Multitask Speech Recognition and Speaker Change Detection for Unknown Number of Speakers
Publication info here.
Authors: Umberto Cappellazzo, Daniele Falavigna & Alessio Brutti
Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters
Publication info here.
Authors: Bolaji Yusuf, Jan “Honza” Cernocky & Murat Saraclar
Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units
Publication info here.
Authors: Jan Pesan, Vojtech Jurık, Martin Karafiat & Jan Cernocky
BESST Dataset: A Multimodal Resource for Speech-based Stress Detection and Analysis
Publication info here.
Authors: Christos Vlachos, Themos Stafylakis & Ion Androutsopoulos
Comparing Data Augmentation Methods for End-to-End Task-Oriented Dialog Systems
Publication info here.
Authors: Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti & Mirco Ravanelli
Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers
Publication info here.
Authors: Magdalena Biesialska, David Solans, Jordi Luque & Carlos Segura
On the Relationship of Social Gender Equality and Grammatical Gender in Pre-trained Large Language Models
Publication info here.
Authors: Sergio Burdisso, Srikanth Madikeri & Petr Motlicek
Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction
Publication info here.
Authors: Shashi Kumar, et al
TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR
Publication info here.
Authors: Umberto Cappellazzo, Minsu Kim, Honglie Chen, Pingchuan Ma, Stavros Petridis, Daniele Falavigna, Alessio Brutti, & Maja Pantic
Large Language Models are Strong Audio-Visual Speech Recognition Learners
Publication info here.
Authors: Muhammad A. Shah, David Solans, Mikko A. Heikkilä, Bhiksha Raj & Nicolas Kourtellis
Speech robust bench: A robustness benchmark for speech recognition
Publication info here.
Authors: Javier García Gilabert, Carlos Escolano, Audrey Mash, Xixian Liao & Maite Melero
MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation
Publication info here.
Authors: Shashi Kumar, Srikanth Madikeri, Juan Zuluaga-Gomez, Esaú Villatoro-Tello, Iuliia Thorbecke, Petr Motlicek, Manjunath K E, and Aravind Ganapathiraju
XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models
Publication info here.
Authors: Umberto Cappellazzo, Minsu Kim, Stavros Petridis, Daniele Falavigna & Alessio Brutti
Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach
Publication info here.
Authors: Aleksandar Armacki, Pranay Sharma, Gauri Joshi, Dragana Bajović, Dušan Jakovetić and Soummya Kar
High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise
Publication info here.
Authors: Šimon Sedlaček, Bolaji Yusuf, Jan Švec, Pradyoth Hegde, Santosh Kesiraju, Oldrich Plchot, Jan Černocky
Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs
Publication info here.
Authors: Pradyoth Hegde, Santosh Kesiraju, Ján Švec, Šimon Sedláček, Bolaji Yusuf, Oldrich Plchot, Deepak K T, Jan Cernocký
Factors affecting the in-context learning abilities of LLMs for dialogue state tracking
Publication info here.
Authors: Alexander Polok, Jiangyu Han , Dominik Klement, Samuele Cornell, Jan Černocky, Lukaš Burget
BUT System for the MLC-SLM Challenge
Publication info here.
Authors: Christos Vlachos, Nikolaos Stylianou, Alexandra Fiotaki, Spiros Methenitis, Elisavet Palogiannidi, Themos Stafylakis, Ion Androutsopoulos
Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questions
Publication info here.
Authors: Alexander Polok, Dominik Klement, Jiangyu Han, Šimon Sedlaček, Bolaji Yusuf, Matthew Maciejewski, Matthew Wiesner, Lukaš Burget
BUT/JHU System Description for CHiME-8 NOTSOFAR-1 Challenge
Publication info here.
Authors: Johan Rohdin, Lin Zhang, Oldrich Plchot, Vojtech Stanček, David Mihola, Junyi Peng, Themos Stafylakis, Dmitriy Beveraki, Anna Silnova, Jan Brukner, Lukaš Burget
BUT Systems and Analyses for the ASVspoof 5 Challenge
Publication info here.
Authors: Dario Badagliacca, Gabriele Caruso, Agnese Augello, Luca Sabatucci
Graph of Goal-Oriented Thoughts: Design and Implementation of LLM Agents
Publication info here.
Authors: Luigi Casoria, Pietro Neroni, Luca Sabatucci, Agnese Augello, Giuseppe Caggianese
Evaluating LLMs for Synthetic Personas Generation: A Comparative Analysis of Personality Representation and Censorship Effects
Publication info here.
Authors: Seraphina Fong, Marco Matassoni, Alessio Brutti
Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages
Publication info here.
Authors: Seraphina Fong, Marco Matassoni, Alessio Brutti
Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages
Publication info here.
Newsletter Issues
Find insights from our expert community, details on our research progress, and information on upcoming events. Join us as we advance the standards in conversational AI and ensure our technologies meet the highest ethical and technical benchmarks.
Discover how an international consortium of experts is pushing the boundaries of AI research, ensuring ethical, secure, and context-aware solutions for a fast-evolving digital world.
Find insights from our successful plenary meeting in Novi Sad to the launch of our BlueSky social media account and the preparations for upcoming ‘Women in AI’ campaign. Explore where Consortium went and more about new publications.
This Issue brings you a glimpse into the milestones achieved through collaboration and innovation within the ELOQUENCE project. The Women in AI campaign enlightened plenty of incredible women who patiently create environments and everyday lives easier. Join us as we look back at the highlights, celebrate our achievements, and set the stage for an even more impactful 2025.
Find a lineup of new blogs featuring cutting-edge AI insights, details on must-attend events that bring together visionary tech leaders, and a glimpse of upcoming events designed to inspire and connect our growing community.
This month, we’re bringing you inspirational upcoming events where you can connect with AI and deep tech innovators, along with insights from our partners’ latest engagements across Europe!
In this issue, you’ll find a fresh wave of updates, including a brand-new podcast episode, our latest scientific publications, and upcoming events where ELOQUENCE will be featured.
As summer shines with vibrant energy, so does the ELOQUENCE AI project. In this issue, you’ll discover our latest achievements, from new scientific publications and inspiring events, to fresh podcast episodes and exciting collaborations across Europe.
As autumn begins, the ELOQUENCE AI project continues to move forward. In this issue, you’ll find our latest updates, including new scientific publications, events, podcast episodes, and collaborations across Europe.
Artificial Intelligence is transforming how we communicate, learn and interact, but its future depends on the people who use it!
That’s why we are launching the ELOQUENCE Europe-wide Survey 2025 and inviting you to share your views on AI adoption, trust, inclusiveness and societal expectations across Europe.
Scientific posters
SEPLN conference
Our project Coordinator, Jordi Luque Serrano presented the scientific poster at the 40th International Conference of the Spanish Society for Natural Language Processing.
AISV conference
Our partner Marco Matassoni, from Fondazione Bruno Kessler, presented the scientific poster at the 21st Convegno Nazionale AISV conference.
Interspeech conference
MLC-SLM challenge
