13 citations · 40 across the 16 of their papers we have counts for
18 papers
The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge
Jordi Luque, Lorenzo Concina, Marco Matassoni +2
This paper details the Eloquence team's approach to Task 2 of the 2nd MLC-SLM challenge at Interspeech 2026, which involves multilingual Multiple-Choice Question Answering (MCQA) a…
MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond
Lorenzo Concina, Seraphina Fong, Marco Matassoni +1
Lightweight projectors are an established way to connect pre-trained speech encoders with large language models (LLMs), mapping acoustic features into token-level embeddings for ta…
LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering
Nina Hosseini-Kivanani, Marco Matassoni, Alessio Brutti
Spoken Question Answering (SQA) remains largely focused on high-resource languages and carefully recorded speech, limiting the reach of speech-LLM methods in low-resource settings.…
Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages
Seraphina Fong, Marco Matassoni, Alessio Brutti
Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art performance in various tasks. However, the…
The Eloquence team submission for task 1 of MLC-SLM challenge
Lorenzo Concina, Jordi Luque, Alessio Brutti +2
In this paper, we present our studies and experiments carried out for the task 1 of the Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM), which…
FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian
Sara Papi, Marco Gaido, Luisa Bentivogli +6
The development of speech foundation models (SFMs) like Whisper and SeamlessM4T has significantly advanced the field of speech processing. However, their closed nature--with inacce…
The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence
Marco Gaido, Sara Papi, Luisa Bentivogli +6
Training large-scale models presents challenges not only in terms of resource requirements but also in terms of their convergence. For this reason, the learning rate (LR) is often…
MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
Marco Gaido, Sara Papi, Luisa Bentivogli +6
The rise of foundation models (FMs), coupled with regulatory efforts addressing their risks and impacts, has sparked significant interest in open-source models. However, existing s…
L2 proficiency assessment using self-supervised speech representations
Stefano Bannò, Kate M. Knill, Marco Matassoni +2
There has been a growing demand for automated spoken language assessment systems in recent years. A standard pipeline for this process is to start with a speech recognition system…
Proficiency assessment of L2 spoken English using wav2vec 2.0
Stefano Bannò, Marco Matassoni
The increasing demand for learning English as a second language has led to a growing interest in methods for automatically assessing spoken language proficiency. Most approaches us…
Seed Words Based Data Selection for Language Model Adaptation
Roberto Gretter, Marco Matassoni, Daniele Falavigna
We address the problem of language model customization in applications where the ASR component needs to manage domain-specific terminology; although current state-of-the-art speech…
Mixtures of Deep Neural Experts for Automated Speech Scoring
Sara Papi, Edmondo Trentin, Roberto Gretter +2
The paper copes with the task of automatic assessment of second language proficiency from the language learners' spoken responses to test prompts. The task has significant relevanc…
Experiments of ASR-based mispronunciation detection for children and adult English learners
Nina Hosseini-Kivanani, Roberto Gretter, Marco Matassoni +1
Pronunciation is one of the fundamentals of language learning, and it is considered a primary factor of spoken language when it comes to an understanding and being understood by ot…
Learning to Rank Microphones for Distant Speech Recognition
Samuele Cornell, Alessio Brutti, Marco Matassoni +1
Fully exploiting ad-hoc microphone networks for distant speech recognition is still an open issue. Empirical evidence shows that being able to select the best microphone leads to s…
TLT-school: a Corpus of Non Native Children Speech
Roberto Gretter, Marco Matassoni, Stefano Bannò +1
This paper describes "TLT-school" a corpus of speech utterances collected in schools of northern Italy for assessing the performance of students learning both English and German. T…
Non-native children speech recognition through transfer learning
Marco Matassoni, Roberto Gretter, Daniele Falavigna +1
This work deals with non-native children's speech and investigates both multi-task and transfer learning approaches to adapt a multi-language Deep Neural Network (DNN) to speakers,…
Automatic Quality Estimation for ASR System Combination
Shahab Jalalvand, Matteo Negri, Daniele Falavigna +2
Recognizer Output Voting Error Reduction (ROVER) has been widely used for system combination in automatic speech recognition (ASR). In order to select the most appropriate words to…
DNN adaptation by automatic quality estimation of ASR hypotheses
Daniele Falavigna, Marco Matassoni, Shahab Jalalvand +2
In this paper we propose to exploit the automatic Quality Estimation (QE) of ASR hypotheses to perform the unsupervised adaptation of a deep neural network modeling acoustic probab…