Aristomenis S. Lampropoulos

MUSIPER: a system for modeling music similarity perception based on objective feature subset selection

We explore the use of objective audio signal features to model the individualized (subjective) perception of similarity between music files. We present MUSIPER, a content-based music retrieval system which constructs music similarity perception models of its users by associating different music similarity measures to different users. Specifically, a user-supplied relevance feedback procedure and related neural network-based incremental learning allows the system to determine which subset of a set of objective features approximates more accurately the subjective music similarity perception of a specific user. Our implementation and evaluation of MUSIPER verifies the relation between subsets of objective features and individualized music similarity perception and exhibits significant improvement in individualized perceived similarity in subsequent music retrievals.

A Cascade-Hybrid Music Recommender System for mobile services based on musical genre classification and personality diagnosis

In this paper, we present a Cascade-Hybrid Music Recommender System intended to operate as a mobile service. Specifically, our system is a middleware that realizes the recommendation process based on a combination of music genre classification and personality diagnosis. A mobile user is able to query for music files by simply sending an example music file from his/her mobile device. In response to the user query, the system recommends music files that not only belong to the same genre as the user query, but also an attempt has been made to take into account both the user preferences as well as ratings from other users for candidate results. The recommendation mechanism is realized by applying the collaborative filtering technique of personality diagnosis. Using the minimum absolute error and the ranked scoring criteria, our approach is compared to existing recommendation techniques that rely on either collaborative filtering or content-based approaches. The outcome of the comparison clearly indicates that our approach exhibits significantly higher performance.

Individualization of music similarity perception via feature subset selection

We address the problem of modeling the subjective perception of similarity between two music files that have been extracted from a music database with use of objective features. We propose the importation of user models in content-based music retrieval systems, which embody the ability of evolving and using different music similarity measures for different users. Specifically, a user-supplied relevance feedback procedure allows the system to determine which subset of a set of objective features approximates more efficiently the subjective music similarity of a specific user. Our implementation of the proposed system verifies our hypothesis and exhibits significant improvement in perceived music similarity

ALIMOS: a middleware system for a ccessing digital music LI braries in MO bile s ervices

We present a software tool, called ALIMOS, for accessing digital music libraries in mobile telecommunication services. The tool provides a semi-automatic interface that allows users to interact with their digital music library in a flexible way based on a combination of content and semantic information. The system architecture is based on a multi-tier application with a front-end and a back-end level. ALIMOS is fully implemented and relevant evaluation results are given.

Accessing the content of Greek historical documents

In this paper, we propose an alternative method for accessing the content of Greek historical documents printed during the 17th and 18th centuries by searching words directly in digitized documents based on word spotting, without the use of an optical character recognition engine. We describe a methodology according to which synthetic word images are created from keywords. These images are compared to all the words in the digitized documents while user feedback is used in order to refine the search procedure. In order to improve the efficiency of accessing and searching, we have used natural language processing techniques that comprise (i) a morphological generator for early Modern Greek which provides the users with the ability to search documents using only a word stem and locate all the corresponding inflected word forms and (ii) a synonym dictionary which facilitates access to the semantic context of documents and enriches the results of the search process.

Evaluation of a Cascade Hybrid Recommendation as a Combination of One-Class Classification and Collaborative Filtering

This paper decomposes the problem of recommendation into a two level cascade recommendation scheme which benefits from both content-based and collaborative filtering methodologies. The first level utilizes the content-based features of items in order to incorporate the individualized (subjective) user preferences within the recommendation process. This is achieved through the exploitation of the one-class classification paradigm which provides the means in order to filter out user specific undesirable items. The second level, on the other hand, serves the purpose of assigning particular rating degrees to the user-specific desirable items identified by the first level. The combination of two approaches in a cascade form, mimics the social process when someone has selected some items according to his preferences and asks for opinions about these by others, in order to achieve the best selection. Our experimentation provides significant evidence on the recommendation efficiency of the adapted hybrid approach which outperforms pure content-based and pure collaborative techniques.

Evaluation of MPEG-7 Descriptors for Speech Emotional Recognition

In this paper we explore the ability of MPEG-7- low level audio descriptors to model the seven emotional categories included in the publically available dataset EmoDB. For our experiments we utilized RBF-SVM classifiers. We made a set of experiments where we examined the seven emotional categories. Experimental results showed that MPEG-7 low-level descriptors (especially a combination of Basic spectral and Timbral features) have the ability to achieve accuracy 77.88% which is comparable to other approaches with high-level perceptual descriptors and to human perception evaluation.

Artificial Immune System-Based Music Genre Classification

We present a novel approach for the problem of automated music genre classification, which utilizes an Artificial Immune System (AIS)-based classifier. Our inspiration lies in the observation that the natural immune system has the intrinsic property of self/non-self cell discrimination, especially when the non-self (complementary) space of cells is significantly larger than the class of self cells. The AIS-based classifier that we have built is compared with KNN-, RBF- and SVM-based classifiers in various experiments involving music data. We find that the performance of our classifier is similar to that of the other classifiers when tested in multi-class (eg. four class) problems. On the other hand, it exceeds by a significant margin the performance of the other classifiers when tested in two class problems.

Music genre classification based on ensemble of signals produced by source separation methods

In this paper, we present a system for musical genre classification that uses a preprocessing module to separate corresponding audio signals into three source signals. A feature extraction procedure is applied to each separated signal and the extracted features are fed into an ensemble combination of Support Vector Machine-based classifiers for genre classification. For the source separation task, we examine and compare two relevant algorithms, namely Convolutive Sparse Coding and a Wavelet Packets-based algorithm. We evaluate our system on a music database of four hundred music samples from four different music genres. Experimental results show that there is a higher classification accuracy in applying a source separation algorithm before feature extraction.

Evaluation of a Middleware System for Accessing Digital Music Libraries in Mobile Services

In this paper, we present and discuss the evaluation process of a middleware system that we have developed. Our system facilitates the access to digital music libraries in push technology-based mobile services. Specifically, our system provides a semi-automatic interface that allows users to interact with a digital music library and find/retrieve music files in a flexible way based on a combination of mobile technologies and content-based retrieval techniques. The evaluation process followed three stages, namely user background information collection, system performance evaluation, and overall system assessment. The evaluation results are quite positive in terms of both system performance evaluation, and overall system assessment.