![]() ![]() ![]() ![]() We annotated the note onset and duration with consistent guide lines throught various expressions and a MIDI note do not include any expression data or control change messages. Each note contains onset and offset times which were manually fine-tuned along with the corresponding syllable. The MIDI data consists of monophonic notes. Grapheme level annoation in a plain TXT format We collected the children's songs to avoid the possible copyright issues in commercial pop music Each audio recording is paired with a MIDI transcription file and a lyrics annotation file. Each song is recorded in two separate keys, ranging from 3 to 5 semitones, resulting in a total of 200 audio recordings. The dataset is composed of 50 Korean and 50 English songs sung by a Korean female professional pop singer. The audio recordings are precisely aligned with the MIDI transcriptions and lyrics annotations and so we expect that the dataset can be useful for various singing voice analysis and synthesis tasks. We introduce the Children's Song Dataset (CSD) which contains vocal recordings of 100 children's songs in Korean or English. CSD: Children's Song Dataset for Singing Voice Research Music and Audio Computing Lab, KAIST Official Page Link CSD Dataset Link CSD: Children’s Song Dataset for Singing Voice Research | Music and Audio Computing Lab, KAIST Skip to the content.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |