
GuitarDuets Dataset We present GuitarDuets, a dataset that provides high-quality classical guitar duet recordings alongside midi annotations. The dataset includes approximately three hours of real and synthesized classical guitar duet recordings, with note-level midi annotations for the synthesized duets. During the recording process, four different classical guitars were used to ensure timbral diversity. Some tracks were replayed using different guitars to further enhance timbral diversity and avoid overfitting. The recordings took place in a quiet, acoustically treated room using high-quality condenser microphones (Presonus PM-2), one for each guitar. To address the issue of cross-microphone sound bleeding, a specialized test set of 7 tracks free from such leakage was recorded. Each guitar track was exported as a 44,100 Hz, 16-bit WAV file in stereo format. The dataset is designed for developing and evaluating monotimbral music source separation algorithms. For Academic Purposes, please cite the following publication: M. Glytsos, C. Garoufis, and A. Zlatintsi and P. Maragos, "Classical Guitar Duet Separation using GuitarDuets - A Dataset of Real and Synthesized Guitar Recordings", in Proc. of the 25th Int. Society for Music Information Retrieval Conf., San Francisco, United States, 2024.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
