348 citations · 534 across the 53 of their papers we have counts for
53 papers
Is Natural Always Appropriate? Investigating Naturalness and Appropriateness Across Different Domains for TTS Evaluation
Dominika Woszczyk, Andreas Triantafyllopoulos, Jura Miniota +2
Text-to-speech (TTS) evaluation is an open challenge. While the primary target was "naturalness," recent fidelity gains shifted focus toward "appropriateness" and whether speech is…
CoughPhase-CLR: Designing an acoustics-informed foundation model for coughing sound classification
Marius Moldovan, Anton Batliner, Thomas M. Berghaus +2
In this work, we introduce CoughPhase-CLR, a self-supervised learning framework designed to leverage the physiological phases of a cough for robust representation learning. Unlike…
Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition
Iosif Tsangko, Andreas Triantafyllopoulos, Björn W. Schuller
Instruction-following audio language models (ALMs) can be augmented with explicit acoustic cues, yet it remains unclear whether such cues are used in a grounded way when the raw au…
A Pilot Study on Curator-Guided Multilingual Art Description for Blind and Low-Vision Audiences with Small Vision-Language Models
Iosif Tsangko, Andreas Triantafyllopoulos, George Margetis +2
Blind and low-vision (BLV) audiences remain underserved by visual art descriptions, particularly across languages and in museum settings where privacy and intellectual-property con…
CoarseSoundNet: Building a reliable model for ecological soundscape analysis
Alexander Gebhard, Andreas Triantafyllopoulos, Dominik Arend +4
A soundscape is composed of three types of sound: biophony (sounds made by animals), geophony (natural abiotic sounds) and anthropophony (sounds made by humans). A key research que…
A conceptual framework for learning to listen by reward: Curiosity-driven search for novel sources
Andreas Triantafyllopoulos, Jakub Šťastný, Alexios Terpinas +3
Reinforcement learning is a powerful learning paradigm that has spearheaded progress in numerous domains. Its core promise lies in learning through high-level goals without the nee…
EmoSURA: Towards Accurate Evaluation of Detailed and Long-Context Emotional Speech Captions
Xin Jing, Andreas Triantafyllopoulos, Jiadong Wang +3
Recent advancements in speech captioning models have enabled the generation of rich, fine-grained captions for emotional speech. However, the evaluation of such captions remains a…
How Class Ontology and Data Scale Affect Audio Transfer Learning
Manuel Milling, Andreas Triantafyllopoulos, Alexander Gebhard +2
Transfer learning is a crucial concept within deep learning that allows artificial neural networks to benefit from a large pre-training data basis when confronted with a task of li…
SmoothCLAP: Soft-Target Enhanced Contrastive Language\--Audio Pretraining for Affective Computing
Xin Jing, Jiadong Wang, Andreas Triantafyllopoulos +4
The ambiguity of human emotions poses several challenges for machine learning models, as they often overlap and lack clear delineating boundaries. Contrastive language-audio pretra…
Charting 15 years of progress in deep learning for speech emotion recognition: A replication study
Andreas Triantafyllopoulos, Anton Batliner, Björn W. Schuller
Speech emotion recognition (SER) has long benefited from the adoption of deep learning methodologies. Deeper models -- with more layers and more trainable parameters -- are general…
Detecting COPD Through Speech Analysis: A Dataset of Danish Speech and Machine Learning Approach
Cuno Sankey-Olsen, Rasmus Hvass Olesen, Tobias Oliver Eberhard +3
Chronic Obstructive Pulmonary Disease (COPD) is a serious and debilitating disease affecting millions around the world. Its early detection using non-invasive means could enable pr…
Reading Smiles: Proxy Bias in Foundation Models for Facial Emotion Recognition
Iosif Tsangko, Andreas Triantafyllopoulos, Adem Abdelmoula +2
Foundation Models (FMs) are rapidly transforming Affective Computing (AC), with Vision Language Models (VLMs) now capable of recognising emotions in zero shot settings. This paper…
MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge
Xin Jing, Jiadong Wang, Iosif Tsangko +2
Although speech emotion recognition (SER) has advanced significantly with deep learning, annotation remains a major hurdle. Human annotation is not only costly but also subject to…
ECOSoundSet: a finely annotated dataset for the automated acoustic identification of Orthoptera and Cicadidae in North, Central and temperate Western Europe
David Funosas, Elodie Massol, Yves Bas +23
Currently available tools for the automated acoustic recognition of European insects in natural soundscapes are limited in scope. Large and ecologically heterogeneous acoustic data…
DFingerNet: Noise-Adaptive Speech Enhancement for Hearing Aids
Iosif Tsangko, Andreas Triantafyllopoulos, Michael Müller +2
The DeepFilterNet (DFN) architecture was recently proposed as a deep learning model suited for hearing aid devices. Despite its competitive performance on numerous benchmarks, it s…
autrainer: A Modular and Extensible Deep Learning Toolkit for Computer Audition Tasks
Simon Rampp, Andreas Triantafyllopoulos, Manuel Milling +1
This work introduces the key operating principles for autrainer, our new deep learning training framework for computer audition tasks. autrainer is a PyTorch-based toolkit that all…
Large language models for mental health
Andreas Triantafyllopoulos, Yannik Terhorst, Iosif Tsangko +10
Digital technologies have long been explored as a complement to standard procedure in mental health research and practice, ranging from the management of electronic health records…
Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning
Simon Rampp, Manuel Milling, Andreas Triantafyllopoulos +1
Curriculum learning (CL) describes a machine learning training strategy in which samples are gradually introduced into the training process based on their difficulty. Despite a par…
Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models
Xin Jing, Kun Zhou, Andreas Triantafyllopoulos +1
While current emotional text-to-speech (TTS) systems can generate highly intelligible emotional speech, achieving fine control over emotion rendering of the output speech still rem…
Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importance
Manuel Milling, Shuo Liu, Andreas Triantafyllopoulos +2
Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life appl…
Abusive Speech Detection in Indic Languages Using Acoustic Features
Anika A. Spiesberger, Andreas Triantafyllopoulos, Iosif Tsangko +1
Abusive content in online social networks is a well-known problem that can cause serious psychological harm and incite hatred. The ability to upload audio data increases the import…
Computer Audition: From Task-Specific Machine Learning to Foundation Models
Andreas Triantafyllopoulos, Iosif Tsangko, Alexander Gebhard +3
Foundation models (FMs) are increasingly spearheading recent advances on a variety of tasks that fall under the purview of computer audition -- the use of machines to understand so…
ParaCLAP -- Towards a general language-audio model for computational paralinguistic tasks
Xin Jing, Andreas Triantafyllopoulos, Björn Schuller
Contrastive language-audio pretraining (CLAP) has recently emerged as a method for making audio analysis more generalisable. Specifically, CLAP-style models are able to `answer' a…
Enrolment-based personalisation for improving individual-level fairness in speech emotion recognition
Andreas Triantafyllopoulos, Björn Schuller
The expression of emotion is highly individualistic. However, contemporary speech emotion recognition (SER) systems typically rely on population-level models that adopt a `one-size…