7 citations · 15 across the 19 of their papers we have counts for
21 papers
Personalized Automatic Speech Recognition for a Dysarthric and Tracheostomic Speaker using Artificial Conversations
David Nadrchal, Monorama Swain, Florian Schmid +2
This work presents an automatic speech recognition (ASR) system personalized for a Czech speaker with a permanent tracheal stoma and severe dysarthria rendering their speech uninte…
On Temporal Binding in Large Audio Language Models
Paul Primus, Gerhard Widmer
Reasoning about temporal structure of audio recordings requires Large Audio Language Models (LALMs) to associate sound events with their temporal position. Understanding the underl…
RealDESED: A Real-World Domestic Sound Event Detection Benchmark
Florian Schmid, Paul Primus, Alexander Fichtinger +3
This paper presents RealDESED, a real-world domestic sound event detection (SED) benchmark comprising 5,710 audio recordings collected by 652 participants in their homes. Each reco…
Low-Latency Neural Models for Real-Time Music Enhancement
Emmanouil Karystinaios, Jonathan Greif, David Nadrchal +2
Music recordings and live streams are often affected by noise, reverberation, spectral imbalances, or artifacts that degrade listening quality. While speech enhancement has matured…
TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining
Paul Primus, Florian Schmid, Gerhard Widmer
Learning to associate audio with textual descriptions is valuable for a range of tasks, including pretraining, zero-shot classification, audio retrieval, audio captioning, and text…
Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge
Florian Schmid, Paul Primus, Toni Heittola +3
This paper presents the Low-Complexity Acoustic Scene Classification with Device Information Task of the DCASE 2025 Challenge, along with its baseline system. Continuing the focus…
Effective Pre-Training of Audio Transformers for Sound Event Detection
Florian Schmid, Tobias Morocutti, Francesco Foscarin +3
We propose a pre-training pipeline for audio spectrogram transformers for frame-level sound event detection tasks. On top of common pre-training steps, we add a meticulously design…
Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval
Paul Primus, Florian Schmid, Gerhard Widmer
Dual-encoder-based audio retrieval systems are commonly optimized with contrastive learning on a set of matching and mismatching audio-caption pairs. This leads to a shared embeddi…
Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining
Jonathan Greif, Florian Schmid, Paul Primus +1
Query-by-Vocal Imitation (QBV) is about searching audio files within databases using vocal imitations created by the user's voice. Since most humans can effectively communicate sou…
Improving Audio Spectrogram Transformers for Sound Event Detection Through Multi-Stage Training
Florian Schmid, Paul Primus, Tobias Morocutti +2
This technical report describes the CP-JKU team's submission for Task 4 Sound Event Detection with Heterogeneous Training Datasets and Potentially Missing Labels of the DCASE 24 Ch…
Multi-Iteration Multi-Stage Fine-Tuning of Transformers for Sound Event Detection with Heterogeneous Datasets
Florian Schmid, Paul Primus, Tobias Morocutti +2
A central problem in building effective sound event detection systems is the lack of high-quality, strongly annotated sound event datasets. For this reason, Task 4 of the DCASE 202…
Fusing Audio and Metadata Embeddings Improves Language-based Audio Retrieval
Paul Primus, Gerhard Widmer
Matching raw audio signals with textual descriptions requires understanding the audio's content and the description's semantics and then drawing connections between the two modalit…
Data-Efficient Low-Complexity Acoustic Scene Classification in the DCASE 2024 Challenge
Florian Schmid, Paul Primus, Toni Heittola +4
This article describes the Data-Efficient Low-Complexity Acoustic Scene Classification Task in the DCASE 2024 Challenge and the corresponding baseline system. The task setup is a c…
Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets
Paul Primus, Khaled Koutini, Gerhard Widmer
This work presents a text-to-audio-retrieval system based on pre-trained text and spectrogram transformers. Our method projects recordings and textual descriptions into a shared au…
On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers
Paul Primus and, Gerhard Widmer
Varying conditions between the data seen at training and at application time remain a major challenge for machine learning. We study this problem in the context of Acoustic Scene C…
Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers
Paul Primus, Gerhard Widmer
Standard machine learning models for tagging and classifying acoustic signals cannot handle classes that were not seen during training. Zero-Shot (ZS) learning overcomes this restr…
Improving Natural-Language-based Audio Retrieval with Transfer Learning and Audio & Text Augmentations
Paul Primus, Gerhard Widmer
The absence of large labeled datasets remains a significant challenge in many application areas of deep learning. Researchers and practitioners typically resort to transfer learnin…
Anomalous Sound Detection as a Simple Binary Classification Problem with Careful Selection of Proxy Outlier Examples
Paul Primus, Verena Haunschmid, Patrick Praher +1
Unsupervised anomalous sound detection is concerned with identifying sounds that deviate from what is defined as 'normal', without explicitly specifying the types of anomalies. A s…
Receptive-Field Regularized CNNs for Music Classification and Tagging
Khaled Koutini, Hamid Eghbal-Zadeh, Verena Haunschmid +3
Convolutional Neural Networks (CNNs) have been successfully used in various Music Information Retrieval (MIR) tasks, both as end-to-end models and as feature extractors for more co…
On Data Augmentation and Adversarial Risk: An Empirical Analysis
Hamid Eghbal-zadeh, Khaled Koutini, Paul Primus +5
Data augmentation techniques have become standard practice in deep learning, as it has been shown to greatly improve the generalisation abilities of models. These techniques rely o…
Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification
Paul Primus, Hamid Eghbal-zadeh, David Eitelsebner +3
Distribution mismatches between the data seen at training and at application time remain a major challenge in all application areas of machine learning. We study this problem in th…