| 1. |
- Holzapfel, André, 1976-, et al.
(author)
-
Selective sampling for beat tracking evaluation
- 2012
-
In: IEEE Transactions on Audio, Speech, and Language Processing. - : IEEE Press. - 1558-7916 .- 1558-7924. ; 20:9, s. 2539-2548
-
Journal article (peer-reviewed)abstract
- In this paper, we propose a method that can identify challenging music samples for beat tracking without ground truth. Our method, motivated by the machine learning method "selective sampling," is based on the measurement of mutual agreement between beat sequences. In calculating this mutual agreement we show the critical influence of different evaluation measures. Using our approach we demonstrate how to compile a new evaluation dataset comprised of difficult excerpts for beat tracking and examine this difficulty in the context of perceptual and musical properties. Based on tag analysis we indicate the musical properties where future advances in beat tracking research would be most profitable and where beat tracking is too difficult to be attempted. Finally, we demonstrate how our mutual agreement method can be used to improve beat tracking accuracy on large music collections.
|
|
| 2. |
- Miron, Marius, et al.
(author)
-
Beat Station : A real-time rhythm annotation software
- 2013
-
In: Proceedings of Sound and Music Computing Conference (SMC) 2013. - : Sound and Music Computing. ; , s. 729-734
-
Conference paper (peer-reviewed)abstract
- This paper describes an open-source software for real-time rhythm annotation. The software integrates several modules for graphical user interface, user management across a network, tap recording, audio playing, midi interfacing and threading. It is a powerful tool for conducting listening tests, but can also be used for beat annotation of music or in a game setup. The parameters of this software, including the real-time constraints, are not pre-defined in the code but can be easily changed in a settings file. Finally, the framework used allows for scalability, as it was developed in openFrameworks. We show the usefulness of the software by applying it in a cross-cultural beat tapping experiment during the ISMIR 2012 conference. An analysis of the collected real-time annotations indicates that listeners encounter difficulties in synchronizing to music in presence of unfamiliar rhythmic structures and instrumental timbres.
|
|
| 3. |
- Zapata, Jose Ricardo, et al.
(author)
-
Assigning a confidence threshold on automatic beat annotation in large datasets
- 2012
-
In: Proceedings of ISMIR - International Conference on Music Information Retrieval. ; , s. 157-162
-
Conference paper (peer-reviewed)abstract
- In this paper we establish a threshold for perceptually acceptable beat tracking based on the mutual agreement of a committee of beat trackers. In the first step we use an existing annotated dataset to show that mutual agreement can be used to select one committee member as the most reliable beat tracker for a song. Then we conduct a listening test using a subset of the Million Song Dataset to establish a threshold which results in acceptable quality of the chosen beat output. For both datasets, we obtain a percent age of trackable music of about 73%, and we investigate which data tags are related to acceptable and problematic beat tracking. The results indicate that current datasets are biased towards genres which tend to be easy for beat tracking. The proposed methods provide a means to automatically obtain a confidence value for beat tracking in non-annotated data and to choose between a number of beat tracker outputs.
|
|
