Sebastian Bock
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sebastian Bock has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Gerhard Widmer
Johannes Kepler University Linz Austria
2 shared publications - Andreas Arzt
Johannes Kepler University Linz, Altenberger Str., A-4040 Linz
1 shared publication - António S. Pinto
INESC TEC, Centre for Telecommunications and Multimedia, 4200-465 Porto, Portugal
1 shared publication - Augusto Sarti
Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, 20133 Milan, Italy
1 shared publication Bernhard Lehner
Department of Computational Perception, Johannes Kepler University of Linz, Austria
1 shared publicationBruno Giorgi
1 shared publication
Latest Publications
- Open Access
- 23 June 2021
- Published by MDPI AG in Electronics
- Vol. 10 (13) , 1518
User-Driven Fine-Tuning for Beat Tracking
The extraction of the beat from musical audio signals represents a foundational task in the field of music information retrieval. While great advances in performance have been achieved due the use of deep neural networks, significant shortcomings still remain. In particular, performance is generally much lower on musical content that differs from that which is contained in existing annotated datasets used for neural network training, as well as in the presence of challenging musical conditions such as rubato. In this paper, we positioned our approach to beat tracking from a real-world perspective where an end-user targets very high accuracy on specific music pieces and for which the current state of the art is not effective. To this end, we explored the use of targeted fine-tuning of a state-of-the-art deep neural network based on a very limited temporal region of annotated beat locations. We demonstrated the success of our approach via improved performance across existing annotated datasets and a new annotation-correction approach for evaluation. Furthermore, we highlighted the ability of content-specific fine-tuning to learn both what is and what is not the beat in challenging musical conditions.
- 23 June 2021
- Published by MDPI AG in Electronics
- Vol. 10 (13) , 1518
Open AccessUser-Driven Fine-Tuning for Beat Tracking
The extraction of the beat from musical audio signals represents a foundational task in the field of music information retrieval. While great advances in performance have been achieved due the use of deep neural networks, significant shortcomings still remain. In particular, performance is generally much lower on musical content that differs from that which is contained in existing annotated datasets used for neural network training, as well as in the presence of challenging musical conditions such as rubato. In this paper, we positioned our approach to beat tracking from a real-world perspective where an end-user targets very high accuracy on specific music pieces and for which the current state of the art is not effective. To this end, we explored the use of targeted fine-tuning of a state-of-the-art deep neural network based on a very limited temporal region of annotated beat locations. We demonstrated the success of our approach via improved performance across existing annotated datasets and a new annotation-correction approach for evaluation. Furthermore, we highlighted the ability of content-specific fine-tuning to learn both what is and what is not the beat in challenging musical conditions.
- 11 August 2016
- Published by Audio Engineering Society in Journal of the Audio Engineering Society
- Vol. 64 (7) , 493-502
Multipath Beat Tracking
- 11 August 2016
- Published by Audio Engineering Society in Journal of the Audio Engineering Society
- Vol. 64 (7) , 493-502
Multipath Beat Tracking
- Open Access
- 1 August 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 21-25
A low-latency, real-time-capable singing voice detection method with LSTM recurrent neural networks
Singing voice detection aims at identifying the regions in a music recording where at least one person sings. This is a challenging problem that cannot be solved without analysing the temporal evolution of the signal. Current state-of-the-art methods combine timbral with temporal characteristics, by summarising various feature values over time, e.g. by computing their variance. This leads to more contextual information, but also to increased latency, which is problematic if our goal is on-line, real-time singing voice detection. To overcome this problem and reduce the necessity to include context in the features themselves, we introduce a method that uses Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN). In experiments on several data sets, the resulting singing voice detector outperforms the state-of-the-art baselines in terms of accuracy, while at the same time drastically reducing latency and increasing the time resolution of the detector.
- 1 August 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 21-25
Open AccessA low-latency, real-time-capable singing voice detection method with LSTM recurrent neural networks
Singing voice detection aims at identifying the regions in a music recording where at least one person sings. This is a challenging problem that cannot be solved without analysing the temporal evolution of the signal. Current state-of-the-art methods combine timbral with temporal characteristics, by summarising various feature values over time, e.g. by computing their variance. This leads to more contextual information, but also to increased latency, which is problematic if our goal is on-line, real-time singing voice detection. To overcome this problem and reduce the necessity to include context in the features themselves, we introduce a method that uses Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN). In experiments on several data sets, the resulting singing voice detector outperforms the state-of-the-art baselines in terms of accuracy, while at the same time drastically reducing latency and increasing the time resolution of the detector.
- Top Cited Papers
- 1 May 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 6979-6983
Improved musical onset detection with Convolutional Neural Networks
Musical onset detection is one of the most elementary tasks in music analysis, but still only solved imperfectly for polyphonic music signals. Interpreted as a computer vision problem in spectrograms, Convolutional Neural Networks (CNNs) seem to be an ideal fit. On a dataset of about 100 minutes of music with 26k annotated onsets, we show that CNNs outperform the previous state-of-the-art while requiring less manual preprocessing. Investigating their inner workings, we find two key advantages over hand-designed methods: Using separate detectors for percussive and harmonic onsets, and combining results from many minor variations of the same scheme. The results suggest that even for well-understood signal processing tasks, machine learning can be superior to knowledge engineering.
- 1 May 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 6979-6983
Top Cited PapersImproved musical onset detection with Convolutional Neural Networks
Musical onset detection is one of the most elementary tasks in music analysis, but still only solved imperfectly for polyphonic music signals. Interpreted as a computer vision problem in spectrograms, Convolutional Neural Networks (CNNs) seem to be an ideal fit. On a dataset of about 100 minutes of music with 26k annotated onsets, we show that CNNs outperform the previous state-of-the-art while requiring less manual preprocessing. Investigating their inner workings, we find two key advantages over hand-designed methods: Using separate detectors for percussive and harmonic onsets, and combining results from many minor variations of the same scheme. The results suggest that even for well-understood signal processing tasks, machine learning can be superior to knowledge engineering.
- 1 March 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 121-124
Polyphonic piano note transcription with recurrent neural networks
In this paper a new approach for polyphonic piano note onset transcription is presented. It is based on a recurrent neural network to simultaneously detect the onsets and the pitches of the notes from spectral features. Long Short-Term Memory units are used in a bidirectional neural network to model the context of the notes. The use of a single regression output layer instead of the often used one-versus-all classification approach enables the system to significantly lower the number of erroneous note detections. Evaluation is based on common test sets and shows exceptional temporal precision combined with a significant boost in note transcription performance compared to current state-of-the-art approaches. The system is trained jointly with various synthesized piano instruments and real piano recordings and thus generalizes much better than existing systems.
- 1 March 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 121-124
Polyphonic piano note transcription with recurrent neural networks
In this paper a new approach for polyphonic piano note onset transcription is presented. It is based on a recurrent neural network to simultaneously detect the onsets and the pitches of the notes from spectral features. Long Short-Term Memory units are used in a bidirectional neural network to model the context of the notes. The use of a single regression output layer instead of the often used one-versus-all classification approach enables the system to significantly lower the number of erroneous note detections. Evaluation is based on common test sets and shows exceptional temporal precision combined with a significant boost in note transcription performance compared to current state-of-the-art approaches. The system is trained jointly with various synthesized piano instruments and real piano recordings and thus generalizes much better than existing systems.
- Open Access
- 1 January 2012
- Published by IOS Press
- p. 67-72
Towards a Complete Classical Music Companion
We present a system that listens to music on-line and almost instantly identifies the piece the performers are playing and the exact position in the musical score. This is achieved via a combination of a state-of-the-art audio-to-note transcription algorithm and a novel symbolic fingerprinting method. The speed and precision of the system are evaluated in systematic experiments with a large corpus of classical music recordings. The results indicate extremely fast and accurate recognition performance — a level of performance, in fact, that even human experts in classical music will find hard to match.
- 1 January 2012
- Published by IOS Press
- p. 67-72
Open AccessTowards a Complete Classical Music Companion
We present a system that listens to music on-line and almost instantly identifies the piece the performers are playing and the exact position in the musical score. This is achieved via a combination of a state-of-the-art audio-to-note transcription algorithm and a novel symbolic fingerprinting method. The speed and precision of the system are evaluated in systematic experiments with a large corpus of classical music recordings. The results indicate extremely fast and accurate recognition performance — a level of performance, in fact, that even human experts in classical music will find hard to match.