Downloads provided by UsageCounts
StarNet is an audio collection of 104 classical music pieces obtained from their corresponding free MIDI files, some of which are selected from the MusicNet dataset, and the rest are collected from the Clarinet MIDI Files archive. The pieces include two instrument tracks, and each piece is performed by two instrument sets: strings-piano and clarinet-vibraphone. The dataset has been introduced in the paper "Music-STAR: a Style Translation system for Audio-based Re-instrumentation" and has been used to train models for musical source separation and multi-instrument timbre translation. The repository includes two files, starnet_part1.tar.gz and starnet_part2.tar.gz, each containing 52 pieces. Note that no preprocessing has been applied to the audio files. Six audio files are available per piece, including the mixtures from the two instrument sets and their stems. For instance, the first piece is represented by the following files: 001.0.wav: the clarinet-vibraphone mixture 001.1.wav: the clarinet track 001.2.wav: the vibraphone track 001.3.wav: the strings-piano mixture 001.4.wav: the strings track 001.5.wav: the piano track
music translation, musical source separation, multi-instrument timbre translation, music information retrieval, music
music translation, musical source separation, multi-instrument timbre translation, music information retrieval, music
| citations 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 |
| views | 56 | |
| downloads | 28 |

Views provided by UsageCounts
Downloads provided by UsageCounts