"Polyphonic Singing Datasets for MIR Research" » History » Version 1
Polina Proutskova, 2020-09-18 12:05 AM
| 1 | 1 | Polina Proutskova | h1. "Polyphonic Singing Datasets for MIR Research" |
|---|---|---|---|
| 2 | 1 | Polina Proutskova | |
| 3 | 1 | Polina Proutskova | h2. Abstract: |
| 4 | 1 | Polina Proutskova | |
| 5 | 1 | Polina Proutskova | We showcase two recently published datasets of polyphonic a |
| 6 | 1 | Polina Proutskova | cappella vocal music. Both publicly available datasets form exciting |
| 7 | 1 | Polina Proutskova | research scenarios for music information retrieval (MIR) tasks such as |
| 8 | 1 | Polina Proutskova | (multiple) F0-estimation or source separation in vocal music. First, we |
| 9 | 1 | Polina Proutskova | present the Erkomaishvili dataset, a curated corpus of traditional |
| 10 | 1 | Polina Proutskova | Georgian vocal music. The corpus is based on historic tape recordings of |
| 11 | 1 | Polina Proutskova | three-voice Georgian songs performed by the former master chanter Artem |
| 12 | 1 | Polina Proutskova | Erkomaishvili. Second, we present Dagstuhl ChoirSet, a multitrack |
| 13 | 1 | Polina Proutskova | dataset of "Western" a cappella choral music. The dataset includes |
| 14 | 1 | Polina Proutskova | recordings of an amateur vocal ensemble performing two choir pieces in |
| 15 | 1 | Polina Proutskova | full choir and quartet settings. The audio data was recorded during an |
| 16 | 1 | Polina Proutskova | MIR seminar at Schloss Dagstuhl using different close-up microphones to |
| 17 | 1 | Polina Proutskova | capture the individual singers' voices. |