IDMT-SMT-Bass Dataset

The IDMT-SMT-Bass database is a large database for automatic bass transcription and signal processing.

The overall duration of the audio material is approx. 3.6 hours.

The dataset consists of approx. 4300 WAV files (44.1 kHz, 24bit) with single recorded notes.

Overall, 10 different bass-related playing techniques namely 5 plucking styles

fingerstyle (FS)

picked (PK)

muted (MU)

slap-thumb (ST)

slap-pluck (SP)

and 5 expression styles

normal (NO)

vibrato (VI)

bending (BE)

harmonics (HA)

dead-note (DN)

are incorporated. A further explaination of the playing techniques is provided in

Abeßer, Jakob; Lukashevich, Hanna; Schuller, Gerald: Feature-based extraction of plucking and expression styles of the electric bass guitar, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2010

For each of the three expression techniques (vibrato, bending, slide), two subclasses were defined in:

Abesser, Jakob; Dittmar, Christian; Schuller, Gerald: Automatic Recognition and Parametrization of Frequency Modulation Techniques in Bass-Guitar Recordings, Proceedings of the 42nd AES Conference on Semantic Audio 2011, Ilmenau, Germany

fast vibrato, slow vibrato

semi-tone bending, quarter-note bending

slide up, slide down (recorded with fretless bass guitar)

3 different 4-string electric bass guitars, each with 3 different pick-up settings were used for recording.

The notes cover the common pitch range of a 4-string bass guitar from E1 (41.2 Hz) to G3 (196.0 Hz).