Event-based Multitrack Alignment using a Probabilistic Framework
Bibliographic Data
| ID | 14872147 |
|---|---|
| Authors | Andrew Robertson (0000-0002-0086-0524, Queen Mary University of London, corresponding author), Mark D Plumbley (0000-0002-9708-1075, Queen Mary University of London) |
| Year | 2015 |
| Volume | 44 |
| Issue | 2 |
| Pages | 71-82 |
| Publication date | 2015-04-03 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Journal of New Music Research (JOURNAL) |
| Journal identifiers | ISSN: 0929-8215 • E-ISSN: 1744-5027 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/09298215.2015.1009839 |
| OpenAlex | W1714608692 |
| Language | EN |
| References cited | 10 |
This paper presents a Bayesian probabilistic framework for real-time alignment of a recording or score with a live performance using an event-based approach. Multitrack audio files are processed using existing onset detection and harmonic analysis algorithms to create a representation of a musical performance as a sequence of time-stamped events. We propose the use of distributions for the position and relative speed which are sequentially updated in real-time according to Bayes’ theorem. We develop the methodology for this approach by describing its application in the case of matching a single MIDI track and then extend this to the case of multitrack recordings. An evaluation is presented that contrasts ourmultitrack alignment method with state-of-the-art alignment techniques
Bayesian probability · Data mining · MIDI · Probabilistic logic · Speech recognition · Computer Science · Mathematics · Music and Audio Processing · Music Technology and Sound Studies · Speech and Audio Processing · Artificial Intelligence
| Highly cited | No |
|---|