Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Deep learning for jazz walking bass transcription

: Abeßer, Jakob; Balke, Stefan; Frieler, Klaus; Pfleiderer, Martin; Müller, Meinard

Dittmar, C. ; Audio Engineering Society -AES-:
AES International Conference Semantic Audio 2017. Proceedings : Erlangen, Germany, 22-24 June 2017
Red Hook, NY: Curran, 2017
ISBN: 978-1-5108-4347-9
ISBN: 1-5108-4347-7
International Conference Semantic Audio <2017, Erlangen>
Fraunhofer IDMT ()

In this paper, we focus on transcribing walking bass lines, which provide clues for revealing the actual played chords in jazz recordings. Our transcription method is based on a deep neural network (DNN) that learns a mapping from a mixture spectrogram to a salience representation that emphasizes the bass line. Furthermore, using beat positions, we apply a late-fusion approach to obtain beat-wise pitch estimates of the bass line. First, our results show that this DNN-based transcription approach outperforms state-of-the-art transcription methods for the given task. Second, we found that an augmentation of the training set using pitch shifting improves the model performance. Finally, we present a semi-supervised learning approach where additional training data is generated from predictions on unlabeled datasets.