4 citations · 10 across the 20 of their papers we have counts for
22 papers
Automatic Lyric Transcription for Greek Songs: Scaling and Task Composition Effects in Whisper Adaptation
Maria Frangiadaki, Dimitrios Damianos, Kosmas Kritsis +1
Automatic Lyric Transcription (ALT) remains substantially more challenging than speech recognition due to melodic variability, rhythmic irregularity, and accompaniment interference…
Beyond Magnitude: Contrastive Routing for Modular Mixture-of-Experts
Nikolaos Xiros, Dimitrios Damianos, Maria-Eleni Zoumpoulidi +3
In current Mixture-of-Experts architectures, routing is performed based on representations dominated by structure shared across all tokens, limiting expert specialization. We show…
AmalthAI: An Open-Source Computer Vision Platform for Cultural Heritage
Christos Chatzisavvas, Stelios Alvanos, Efstratios Politis +13
Computer vision (CV) and machine learning (ML) offer new tools for cultural heritage (CH) artifact analysis, but the CV/ML pipeline remains largely inaccessible to CH domain expert…
A Security-Oriented Lifecycle Model for Large Language Model Systems
Eleftherios Batzolis, George Drosatos, Vassilis Katsouros +1
Large language models are being integrated into critical infrastructure and enterprise workflows at unprecedented scale,yet the lifecycle frameworks governing their development and…
Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
Dimitrios Damianos, Leon Voukoutis, Georgios Skyrianos +2
Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood. Existing interpretability wo…
When Slots Compete: Slot Merging in Object-Centric Learning
Christos Chatzisavvas, Panagiotis Rigas, George Ioannakis +2
Slot-based object-centric learning represents an image as a set of latent slots with a decoder that combines them into an image or features. The decoder specifies how slots are com…
Pay (Cross) Attention to the Melody: Curriculum Masking for Single-Encoder Melodic Harmonization
Maximos Kaliakatsos-Papakostas, Dimos Makris, Konstantinos Soiledis +3
Melodic harmonization, the task of generating harmonic accompaniments for a given melody, remains a central challenge in computational music generation. Recent single encoder trans…
Incorporating Structure and Chord Constraints in Symbolic Transformer-based Melodic Harmonization
Maximos Kaliakatsos-Papakostas, Konstantinos Soiledis, Theodoros Tsamis +3
Transformer architectures offer significant advantages regarding the generation of symbolic music; their capabilities for incorporating user preferences toward what they generate i…
Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros +1
Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gende…
A Machine Learning Approach for MIDI to Guitar Tablature Conversion
Maximos Kaliakatsos-Papakostas, Gregoris Bastas, Dimos Makris +3
Guitar tablature transcription consists in deducing the string and the fret number on which each note should be played to reproduce the actual musical part. This assignment should…
VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion
Dimitrios Damianos, Leon Voukoutis, Georgios Paraskevopoulos +1
We present a multimodal fusion framework that bridges pre-trained decoder-based large language models (LLM) and acoustic encoder-decoder architectures such as Whisper, with the aim…
MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions
Georgios Chatzichristodoulou, Despoina Kosmopoulou, Antonios Kritikos +5
SER is a challenging task due to the subjective nature of human emotions and their uneven representation under naturalistic conditions. We propose MEDUSA, a multimodal framework wi…
Krikri: Advancing Open Large Language Models for Greek
Dimitris Roussis, Leon Voukoutis, Georgios Paraskevopoulos +6
We introduce Llama-Krikri-8B, a cutting-edge Large Language Model tailored for the Greek language, built on Meta's Llama 3.1-8B. Llama-Krikri-8B has been extensively trained on hig…
DeepMLF: Multimodal language model with learnable tokens for deep fusion in sentiment analysis
Efthymios Georgiou, Vassilis Katsouros, Yannis Avrithis +1
While multimodal fusion has been extensively studied in Multimodal Sentiment Analysis (MSA), the role of fusion depth and multimodal capacity allocation remains underexplored. In t…
Meltemi: The first open Large Language Model for Greek
Leon Voukoutis, Dimitris Roussis, Georgios Paraskevopoulos +6
We describe the development and capabilities of Meltemi 7B, the first open Large Language Model for the Greek language. Meltemi 7B has 7 billion parameters and is trained on a 40 b…
The Greek podcast corpus: Competitive speech models for low-resourced languages with weakly supervised data
Georgios Paraskevopoulos, Chara Tsoukala, Athanasios Katsamanis +1
The development of speech technologies for languages with limited digital representation poses significant challenges, primarily due to the scarcity of available data. This issue i…
Weakly-supervised Automated Audio Captioning via text only training
Theodoros Kouzelis, Vassilis Katsouros
In recent years, datasets of paired audio and captions have enabled remarkable success in automatically generating descriptions for audio clips, namely Automated Audio Captioning (…
Investigating Personalization Methods in Text to Music Generation
Manos Plitsis, Theodoros Kouzelis, Georgios Paraskevopoulos +2
In this work, we investigate the personalization of text-to-music diffusion models in a few-shot setting. Motivated by recent advances in the computer vision domain, we are the fir…
Weakly-supervised forced alignment of disfluent speech using phoneme-level modeling
Theodoros Kouzelis, Georgios Paraskevopoulos, Athanasios Katsamanis +1
The study of speech disorders can benefit greatly from time-aligned data. However, audio-text mismatches in disfluent speech cause rapid performance degradation for modern speech a…
Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greek
Georgios Paraskevopoulos, Theodoros Kouzelis, Georgios Rouvalis +3
Modern speech recognition systems exhibits rapid performance degradation under domain shift. This issue is especially prevalent in data-scarce settings, such as low-resource langua…
Regotron: Regularizing the Tacotron2 architecture via monotonic alignment loss
Efthymios Georgiou, Kosmas Kritsis, Georgios Paraskevopoulos +3
Recent deep learning Text-to-Speech (TTS) systems have achieved impressive performance by generating speech close to human parity. However, they suffer from training stability issu…
Zero-Shot Cross-lingual Aphasia Detection using Automatic Speech Recognition
Gerasimos Chatzoudis, Manos Plitsis, Spyridoula Stamouli +3
Aphasia is a common speech and language disorder, typically caused by a brain injury or a stroke, that affects millions of people worldwide. Detecting and assessing Aphasia in pati…