Recep Oguz Araz

According to our database, Recep Oguz Araz authored at least 7 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

OMAR-RQ: Open Music Audio Representation Model Trained with Multi-Feature Masked Token Prediction.

Pablo Alonso-Jiménez, Pedro Ramoneda, Recep Oguz Araz, Andrea Poltronieri, Dmitry Bogdanov

CoRR, July, 2025

Enhancing Neural Audio Fingerprint Robustness to Audio Degradation for Music Identification.

Recep Oguz Araz, Guillem Cortès-Sebastià, Emilio Molina, Joan Serrà, Xavier Serra, Yuki Mitsufuji, Dmitry Bogdanov

CoRR, June, 2025

Supervised contrastive learning from weakly-labeled audio segments for musical version matching.

Joan Serrà, Recep Oguz Araz, Dmitry Bogdanov, Yuki Mitsufuji

CoRR, February, 2025

2024

Discogs-VI: A musical version identification dataset based on public editorial metadata.

Recep Oguz Araz, Xavier Serra, Dmitry Bogdanov

Dataset, November, 2024

Discogs-VI: A Musical Version Identification Dataset Based on Public Editorial Metadata.

Recep Oguz Araz, Xavier Serra, Dmitry Bogdanov

Proceedings of the 25th International Society for Music Information Retrieval Conference, 2024

Evaluation of Deep Audio Representations for Semantic Sound Similarity.

Recep Oguz Araz, Dmitry Bogdanov, Pablo Alonso-Jiménez, Frederic Font

Proceedings of the 21st International Conference on Content-Based Multimedia Indexing, 2024

2022

Universal Speech Enhancement with Score-based Diffusion.

Joan Serrà, Santiago Pascual, Jordi Pons, Recep Oguz Araz, Davide Scaini

CoRR, 2022