198,149 research outputs found
MuChoMusic dataset
No full textMuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models
MuChoMusic is a benchmark designed to evaluate music understanding in multimodal language models focused on audio. It includes 1,187 multiple-choice questions validated by human annotators, based on 644 music tracks from two publicly available music datasets. These questions cover a wide variety of genres and assess knowledge and reasoning across several musical concepts and their cultural and functional contexts. The benchmark provides a holistic evaluation of five open-source models, revealing challenges such as over-reliance on the language modality and highlighting the need for better multimodal integration.
Note on Audio Files
This dataset comes without audio files. The audio files can be downloaded from two datasets: SongDescriberDataset (SDD) and MusicCaps. Please see the code repository for more information on how to download the audio.
Citation
If you use this dataset, please cite our paper:
@inproceedings{weck2024muchomusic,
title={MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models},
author={Weck, Benno and Manco, Ilaria and Benetos, Emmanouil and Quinton, Elio and Fazekas, György and Bogdanov, Dmitry},
booktitle = {Proceedings of the 25th International Society for Music Information Retrieval Conference (ISMIR)},
year={2024}
}
Weck B, Manco I, Benetos E, Quinton E, Fazekas G, Bogdanov D. MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models. In: Kaneshiro B, Mysore G, Nieto O, Donahue C, Huang CZA, Lee JH, McFee B, McCallum M, editors. Proceedings of the 25th International Society for Music Information Retrieval Conference (ISMIR2024); 2024 November 10-14; San Francisco, USA
Song Describer Dataset
No full textThe Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation.
A retro-futurist drum machine groove drenched in bubbly synthetic sound effects and a hint of an acid bassline.
The Song Describer Dataset (SDD) contains ~1.1k captions for 706 permissively licensed music recordings. It is designed for use in evaluation of models that address music-and-language (M&L) tasks such as music captioning, text-to-music generation and music-language retrieval. More information about the data, collection method and validation is provided in the paper describing the dataset.
If you use this dataset, please cite our paper:
The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation, Manco, Ilaria and Weck, Benno and Doh, Seungheon and Won, Minz and Zhang, Yixiao and Bogdanov, Dmitry and Wu, Yusong and Chen, Ke and Tovstogan, Philip and Benetos, Emmanouil and Quinton, Elio and Fazekas, György and Nam, Juhan, Machine Learning for Audio Workshop at NeurIPS 2023, 202
Koche auf Vorrat! : Handbuch für die Frischhaltung aller Nahrungsmittel mit den "Weck'schen Einrichtungen"
No full textHrsg.: J. Weck Gmbh, Öflingen, Amt Säckingen (Baden). Im Auftr. der Hrsg. bearb. unter bes. Mitw. der Herren M. Hotop u. E. Michae
Software compensation of machine tool errors due to the weight of machine components and workpiece
No full textSoundDesc: Cleaned and Group-Filtered Splits
No full textThis upload contains dataset splits of SoundDesc [1] and other supporting material for our paper:
Data leakage in cross-modal retrieval training: A case study [arXiv] [ieeexplore]
In our paper, we demonstrated that a data leakage problem in the previously published splits of SoundDesc leads to overly optimistic retrieval results.
Using an off-the-shelf audio fingerprinting software, we identified that the data leakage stems from duplicates in the dataset.
We define two new splits for the dataset: a cleaned split to remove the leakage and a group-filtered to avoid other kinds of weak contamination of the test data.
SoundDesc is a dataset which was automatically sourced from the BBC Sound Effects web page [2]. The results from our paper can be reproduced using clean_split01 and group_filtered_split01.
If you use the splits, please cite our work:
Benno Weck, Xavier Serra, "Data Leakage in Cross-Modal Retrieval Training: A Case Study," ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.10094617.
@INPROCEEDINGS{10094617,
author={Weck, Benno and Serra, Xavier},
booktitle={ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
title={Data Leakage in Cross-Modal Retrieval Training: A Case Study},
year={2023},
volume={},
number={},
pages={1-5},
doi={10.1109/ICASSP49357.2023.10094617}}
References:
[1] A. S. Koepke, A. -M. Oncescu, J. Henriques, Z. Akata and S. Albanie, "Audio Retrieval with Natural Language Queries: A Benchmark Study," in IEEE Transactions on Multimedia, doi: 10.1109/TMM.2022.3149712.
[2] https://sound-effects.bbcrewind.co.uk
Digitale, fachdidaktische und inklusive Lehrkräftebildung durch OER
No full textBasten M, Ferreira González L, Schaller M, Weck H, Fränkel S. Digitale, fachdidaktische und inklusive Lehrkräftebildung durch OER. Presented at the GDCP-Jahrestagung, Goethe-Universität Frankfurt am Main
Barrierefreie OER-Materialien für eine inklusionsorientierte Transformation der fachdidaktischen Lehre – Ergebnisse aus dem Projekt BInQ-Bio
No full textWeck H, Schaller M, Neumann M, Wilken S, Basten M, Fränkel S. Barrierefreie OER-Materialien für eine inklusionsorientierte Transformation der fachdidaktischen Lehre – Ergebnisse aus dem Projekt BInQ-Bio. Presented at the 38. Jahrestagung der Inklusionsforscher*innen, Universität zu Köln
Dendrimers functionalized with membrane-interacting peptides for viral inhibition
No full textRossella Tarallo,1 Tom P Carberry,2 Annarita Falanga,1 Mariateresa Vitiello,3 Stefania Galdiero,1 Massimiliano Galdiero,3 Marcus Weck21Dipartimento di Farmacia, Università di Napoli "Federico II," and DFM Scarl, Napoli, Italia; 2Molecular Design Institute and Department of Chemistry, New York University, New York, NY, USA; 3Dipartimento di Medicina Sperimentale, Seconda Università degli Studi di Napoli, Napoli, ItaliaAbstract: This contribution reports the synthesis of a poly(amide)-based dendrimer functionalized at the termini with a membrane-interacting peptide derived from the herpes simplex virus (HSV) type 1 glycoprotein H, namely gH625-644. This peptide has been shown to interact with model membranes and to inhibit viral infectivity. The peptidodendrimer inhibits both HSV-1 and HSV-2 at a very early stage of the entry process, most likely through an interaction with the viral envelope glycoproteins; thus, preventing the virus from coming into close contact with cellular membranes, a prerequisite of viral internalization. The 50% inhibitory concentration was 100 and 300 nM against HSV-1 and HSV-2 respectively, with no evidence of cell toxicity at these concentrations. These results show that the functionalization of a dendrimer with the peptide sequence derived from an HSV glycoprotein shows promising inhibitory activity towards viruses of the Herpesviridae family.Keywords: peptidodendrimer, antiviral activity, membranotropic peptide
Dr. Duane M. Jackson, Morehouse College, July 2011
No full textThis video is a conversation with Dr. Duane M. Jackson. Dr. Jackson talks about his paper, "Recall and the Serial Position Effect: The Role of Primacy and Recency on Accounting Students' Performance." Jackie Daniel, AUC Woodruff Library, is the interviewer
Mesoscopic, templated self-assembly at the fluid-fluid interface
No full textThis paper demonstrates templated self-assembly-based on capillary forces-of millimeter-scale poly-(dimethylsiloxane) plates suspended at the water-perfluorodecalin interface. The system described abstracts the concept of "templating" from molecular templating and uses it to design millimeter-scale aggregates that self-assemble in ordered structures. This work points the way to new strategies for organizing complex, millimeter-scale structures
- …
