CopyrightItems in 'OpenAIR@RGU', Robert Gordon University Open Access Institutional Repository, are protected by copyright and intellectual property law. If you believe that any material held in 'OpenAIR@RGU' infringes copyright, please contact openair-help@rgu.ac.uk with details. The item will be removed from the repository while the claim is investigated. "NOTICE: this is the author's version of a work that was accepted for publication in Artificial Intelligence. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in ARTIFICIAL INTELLIGENCE, [VOL 219, (2015) This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. AbstractOnline recommender systems are an important tool that people use to find new music. To generate recommendations, many systems rely on tag representations of music. Such systems however suffer from tag sparsity, whereby tracks lack a strong tag representation. Current state-of-the-art techniques that reduce this sparsity problem create hybrid systems using multiple representations, for example both content and tags. In this paper we present a novel hybrid representation that augments sparse tag representations without introducing content directly. Our hybrid representation integrates pseudotags learned from content into the tag representation of a track, and a dynamic weighting scheme limits the number of pseudo-tags that are allowed to contribute. Experiments demonstrate that this method allows tags to remain dominant when they provide a strong representation, and pseudo-tags to take over when tags are sparse. We show that our approach significantly improves recommendation quality not only for queries with a sparse tag representation, but also those that are well-tagged. Our hybrid approach has potential to be extended to other music representations that are used for recommendation, but suffer from data sparsity, such as user profiles.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-24586-7_6 Abstract. Millions of people use online music services every day and recommender systems are essential to browse these music collections. Users are looking for high quality recommendations, but also want to discover tracks and artists that they do not already know, newly released tracks, and the more niche music found in the 'long tail' of on-line music. Tag-based recommenders are not effective in this 'long tail' because relatively few people are listening to these tracks and so tagging tends to be sparse. However, similarity neighbourhoods in audio space can provide additional tag knowledge that is useful to augment sparse tagging. A new recommender exploits the combined knowledge, from audio and tagging, using a hybrid representation that extends the track's tag-based representation by adding semantic knowledge extracted from the tags of similar music tracks. A user evaluation and a larger experiment using Last.fm user data both show that the new hybrid recommender provides better quality recommendations than using only tags, together with a higher level of discovery of unknown and niche music. This approach of augmenting the representation for items that have missing information, with corresponding information from similar items in a complementary space, offers opportunities beyond content-based music recommendation.

Abstract. This paper presents a novel approach to music genre classification. Having represented music tracks in the form of two dimensional images, we apply the "bag of visual words" method from visual IR in order to classify the songs into 19 genres. By switching to visual domain, we can abstract from musical concepts such as melody, timbre and rhythm. We obtained classification accuracy of 46% (with 5% theoretical baseline for random classification) which is comparable with existing state-of-the-art approaches. Moreover, the novel features characterize different properties of the signal than standard methods. Therefore, the combination of them should further improve the performance of existing techniques. The motivation behind this work was the hypothesis, that 2D images of music tracs (spectrograms) perceived as similar would correspond to the same music genres. Conversely, it is possible to treat real life images as spectrograms and utilize music-based features to represent these images in a vector form. This points to an interesting interchangeability between visual and music information retrieval.

Techniques for music recommendation are increasingly relying on hybrid representations to retrieve new and exciting music. A key component of these representations is musical content, with texture being the most widely used feature. Current techniques for representing texture however are inspired by speech, not music, therefore music representations are not capturing the correct nature of musical texture. In this paper we investigate two parts of the well-established mel-frequency cepstral coefficients (MFCC) representation: the resolution of mel-frequencies related to the resolution of musical notes; and how best to describe the shape of texture. Through contextualizing these parts, and their relationship to music, a novel music-inspired texture representation is developed. We evaluate this new texture representation by applying it to the task of music recommendation. We use the representation to build three recommendation models, based on current state-of-the-art methods. Our results show that by understanding two key parts of texture representation, it is possible to achieve a significant recommendation improvement. This contribution of a music-inspired texture representation will not only improve content-based representation, but will allow hybrid systems to take advantage of a stronger content component.