Cognition-based Segmentation for Music Information Retrieval Systems
Bibliographic Data
| ID | 5304646 |
|---|---|
| Authors | Frans Wiering (0000-0002-2984-8932, Utrecht University, corresponding author), Justin De Nooijer, Anja Volk (0000-0002-6755-9592, Utrecht University), Hermi J M Tabachneck-Schijf |
| Year | 2009 |
| Volume | 38 |
| Issue | 2 |
| Pages | 139-154 |
| Publication date | 2009-06-01 |
| Peer Reviewed | Yes |
| 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 | 10.1080/09298210903171145 |
| OpenAlex | W2001709204 |
| Language | EN |
| Citations received | 1 |
| References cited | 18 |
This paper investigates the generic problem of model selection in the specific context of Music Information Retrieval (MIR). In MIR research, similarity measures are developed for ranking musical items with respect to their relevance to a user's musical query. The application of such similarity measures in MIR systems typically requires musical works to be divided into more manageable units. This involves two tasks: melody segmentation and voice separation. For both of these tasks, several computational models have been proposed in the symbolic domain. It seems reasonable to assume that those solutions that are most in accordance with human performance will result in the best ranking of retrieval output. We conducted two experiments, each with twenty experts and twenty novices. In the melody segmentation experiment, we found a high agreement between the participants. Evaluating algorithm output against participant data, we conclude that human output cannot be distinguished from three of the segmentation algorithms (Grouper, IDyOM and LBDM). For voice separation—which we evaluated by means of a melody identification task—the situation is different, as the combined results of two algorithms (Skyline and SSA) were shown to agree best with experimental results, and differences were found between novice and expert performance. Several other model selection criteria besides performance are discussed in conclusion
Information retrieval · Machine learning · Music Information Retrieval · Musical · Natural language processing · Segmentation · Speech recognition · Computer Science · Music and Audio Processing · Music Technology and Sound Studies · Neuroscience and Music Perception · Artificial Intelligence
Introduction to Information Retrieval
Auditory Scene Analysis
Transportation distances and human perception of melodic similarity
Towards Greater Objectivity in Music Theory
The Equivalence of Weighted Kappa and the Intraclass Correlation Coefficient as Measures of Reliability
Segmentation of Hungarian Folk Songs Using an Entropy-Based Learning System
Memory-Based Models of Melodic Analysis
| Unique citing works | 1 |
|---|---|
| Citations per year | 0,06 |
| Citation span | 2009 - 2009 (1) |
| Citation velocity | historical |
| Highly cited | No |