Similarity in music is a concept with significant impact on ethnomusicology studies, music recommendation systems, and music information retrieval systems such as Shazam and SoundHound. Various computer-based melody similarity measures have been proposed, but comparison and evaluation of similarity measures is inherently difficult due to the subjective and application-dependent nature of similarity in music. In this thesis, we address the diversity of the problem by defining a set of music transformations that provide the criteria for comparing and evaluating melody similarity measures. This approach provides a flexible and extensible method for characterizing selected facets of melody similarity, because the set of music transformations can be tailored to the user and to the application. We demonstrate this approach using three music transformations (transposition, tempo rescaling, and selected forms of ornamentation) to compare and evaluate several existing similarity measures, including String Edit Distance measures, Geometric measures, and N-Gram based measures. We also evaluate a newly implemented distance measure, the Beat and Direction Distance Measure, which is designed to have greater awareness of the beat hierarchy and better responsiveness to ornamentation. Training and test data is drawn from music incipits from the RISM A/II collection, and ground truth is taken from the MIREX 2005 Symbolic Melodic Similarity task. Our test results show that similarity measures that are responsive to music transformations generally have better agreement with human generated ground truth. / Thesis (Master, Computing) -- Queen's University, 2012-08-31 11:03:01.167

With the volume of digital media available today, automatic music recommendation services have proven a useful tool for consumers, allowing them to better discover new and enjoyable music. Typically, this technology is based on collaborative filtering techniques, employing human-generated metadata to base recommendations. Recently, work in content-based recommendation systems have emerged in which the audio signal itself is analyzed for relevant musical information from which models are built that attempt to mimic human similarity judgments. The current state-of-the-art for content-based music recommendation uses a timbre model based on MFCCs calculated on short segments of tracks. These feature vectors are then modeled using GMMs (Gaussian mixture models). GMM modeling of frame-based MFCCs has been shown to perform fairly well on timbre similarity tasks. However, a common problem is that of hubs , in which a relative small number of songs falsely appear similar to many other songs, significantly decreasing the accuracy of similarity recommendations. In this thesis, we explore the origins of hubs in timbre-based modeling and propose several remedies. Specifically, we find that a process of model homogenization, in which certain components of a mixture model are systematically removed, improves performance as measured against several ground-truth similarity metrics. Extending the work of Aucouturier, we introduce several new methods of homogenization. On a subset of the uspop data set, model homogenization improves artist R-precision by a maximum of 3.5% and agreement to user collection co-occurrence data by 7.4%. We also find differences in the effectiveness of the various homogenization methods for hub reduction, with the proposed methods providing the best results. Further, we extend the modeling of frame-based MFCC features by using a kernel density estimation approach to non-parametric modeling. We find that such an approach significantly reduces the number of hubs (by 2.6% of the dataset) while improving agreement to ground-truth by 5% and slightly improving artist R-precision as compared with the standard parametric model. Finally, to test whether these principles hold for all musical data, we introduce an entirely new data set consisting of Indian classical music. We find that our results generalize here as well, suggesting that hubness is a general feature of timbre-based similarity music modeling and that the techniques presented to improve this modeling are effective for diverse types of music.

Similarity computation is a difficult issue in music information retrieval tasks, because it tries to emulate the special ability that humans show for pattern recognition in general, and particularly in the presence of noisy data. A number of works have addressed the problem of what is the best representation for symbolic music in this context. The tree representation, using rhythm for defining the tree structure and pitch information for leaf and node labelling has proven to be effective in melodic similarity computation. In this dissertation we try to built a system that allowed to classify and generate melodies using the information from the tree encoding, capturing the inherent dependencies which are inside this kind of structure, and improving the current methods in terms of accuracy and running time. In this way, we try to find more efficient methods that is key to use the tree structure in large datasets. First, we study the possibilities of the tree edit similarity to classify melodies using a new approach for estimate the weights of the edit operations. Once the possibilities of the cited approach are studied, an alternative approach is used. For that a grammatical inference approach is used to infer tree languages. The inference of these languages give us the possibility to use them to classify new trees (melodies).

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal.

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal

Today, the advent of networking technologies and computer hardware have enabled more and more inexpensive PCs, various mobile devices, smart phones, PDAs, sensors and cameras to be linked to the Internet with better connectivity. In recent years, we have witnessed the emergence of several instances of distributed applications, providing infrastructures for social interactions over large-scale wide-area networks and facilitating the ways users share and publish data. User generated data today range from simple text files to (semi-) structured documents and multimedia content. With the emergence of Semantic Web, the number of features (associated with a content) that are used in order to index those large amounts of heterogenous pieces of data is growing dramatically. The feature sets associated with each content type can grow continuously as we discover new ways of describing a content in formulated terms. As the number of dimensions in the feature data grow (as high as 100 to 1000), it becomes harder and harder to search for information in a dataset due to the curse of dimensionality and it is not appropriate to use naive search methods, as their performance degrade to linear search. As an alternative, we can distribute the content and the query processing load to a set of peers in a distributed Peer-to-Peer (P2P) network and incorporate high-dimensional distributed search techniques to attack the problem. Currently, a large percentage of Internet traffic consists of video and music files shared and exchanged over P2P networks. In most present services, searching for music is performed through keyword search and naive string-matching algorithms using collaborative filtering techniques which mostly use tag based approaches. In music information retrieval (MIR) systems, the main goal is to make recommendations similar to the music that the user listens to. In these systems, techniques based on acoustic feature extraction can be employed to achieve content-based music similarity search (i.e., searching through music based on what can be heard from the music track). Using these techniques we can devise an automated measure of similarity that can replace the need for human experts (or users) who assign descriptive genre tags and meta-data to each recording and solve the famous cold-start problem associated with the collaborative filtering techniques. In this work we explore the advantages of distributed structures by efficiently distributing the content features and query processing load on the peers in a P2P network. Using a family of Locality Sensitive Hash (LSH) functions based on p-stable distributions we propose an efficient, scalable and load-balanced system, capable of performing K-Nearest-Neighbor (KNN) and Range queries. We also propose a new load-balanced indexing algorithm and evaluate it using our Java based simulator. Our results show that this P2P design ensures load-balancing and guarantees logarithmic number of hops for query processing. Our system is extensible to be used with all types of multi-dimensional feature data and it can also be employed as the main indexing scheme of a multipurpose recommendation system. / Graduate

Ce mémoire est composé de trois articles qui s’unissent sous le thème de la recommandation musicale à grande échelle. Nous présentons d’abord une méthode pour effectuer des recommandations musicales en récoltant des étiquettes (tags) décrivant les items et en utilisant cette aura textuelle pour déterminer leur similarité. En plus d’effectuer des recommandations qui sont transparentes et personnalisables, notre méthode, basée sur le contenu, n’est pas victime des problèmes dont souffrent les systèmes de filtrage collaboratif, comme le problème du démarrage à froid (cold start problem). Nous présentons ensuite un algorithme d’apprentissage automatique qui applique des étiquettes à des chansons à partir d’attributs extraits de leur fichier audio. L’ensemble de données que nous utilisons est construit à partir d’une très grande quantité de données sociales provenant du site Last.fm. Nous présentons finalement un algorithme de génération automatique de liste d’écoute personnalisable qui apprend un espace de similarité musical à partir d’attributs audio extraits de chansons jouées dans des listes d’écoute de stations de radio commerciale. En plus d’utiliser cet espace de similarité, notre système prend aussi en compte un nuage d’étiquettes que l’utilisateur est en mesure de manipuler, ce qui lui permet de décrire de manière abstraite la sorte de musique qu’il désire écouter. / This thesis is composed of three papers which unite under the general theme of large-scale music recommendation. The first paper presents a recommendation technique that works by collecting text descriptions of items and using this textual aura to compute the similarity between them using techniques drawn from information retrieval. We show how this representation can be used to explain the similarities between items using terms from the textual aura and further how it can be used to steer the recommender. Because our system is content-based, it is not victim of the usual problems associated with collaborative filtering recommenders like the cold start problem. The second paper presents a machine learning model which automatically applies tags to music. The model uses features extracted from the audio files and was trained on a very large data set constructed with social data from the online community Last.fm. The third paper presents an approach to generating steerable playlists. We first demonstrate a method for learning song transition probabilities from audio features extracted from songs played in professional radio station playlists. We then show that by using this learnt similarity function as a prior, we are able to generate steerable playlists by choosing the next song to play not simply based on that prior, but on a tag cloud that the user is able to manipulate to express the high-level characteristics of the music he wishes to listen to.

Ce mémoire est composé de trois articles qui s’unissent sous le thème de la recommandation musicale à grande échelle. Nous présentons d’abord une méthode pour effectuer des recommandations musicales en récoltant des étiquettes (tags) décrivant les items et en utilisant cette aura textuelle pour déterminer leur similarité. En plus d’effectuer des recommandations qui sont transparentes et personnalisables, notre méthode, basée sur le contenu, n’est pas victime des problèmes dont souffrent les systèmes de filtrage collaboratif, comme le problème du démarrage à froid (cold start problem). Nous présentons ensuite un algorithme d’apprentissage automatique qui applique des étiquettes à des chansons à partir d’attributs extraits de leur fichier audio. L’ensemble de données que nous utilisons est construit à partir d’une très grande quantité de données sociales provenant du site Last.fm. Nous présentons finalement un algorithme de génération automatique de liste d’écoute personnalisable qui apprend un espace de similarité musical à partir d’attributs audio extraits de chansons jouées dans des listes d’écoute de stations de radio commerciale. En plus d’utiliser cet espace de similarité, notre système prend aussi en compte un nuage d’étiquettes que l’utilisateur est en mesure de manipuler, ce qui lui permet de décrire de manière abstraite la sorte de musique qu’il désire écouter. / This thesis is composed of three papers which unite under the general theme of large-scale music recommendation. The first paper presents a recommendation technique that works by collecting text descriptions of items and using this textual aura to compute the similarity between them using techniques drawn from information retrieval. We show how this representation can be used to explain the similarities between items using terms from the textual aura and further how it can be used to steer the recommender. Because our system is content-based, it is not victim of the usual problems associated with collaborative filtering recommenders like the cold start problem. The second paper presents a machine learning model which automatically applies tags to music. The model uses features extracted from the audio files and was trained on a very large data set constructed with social data from the online community Last.fm. The third paper presents an approach to generating steerable playlists. We first demonstrate a method for learning song transition probabilities from audio features extracted from songs played in professional radio station playlists. We then show that by using this learnt similarity function as a prior, we are able to generate steerable playlists by choosing the next song to play not simply based on that prior, but on a tag cloud that the user is able to manipulate to express the high-level characteristics of the music he wishes to listen to.