Saltar apartados

Research Project

Descripción y recuperación de información musical y sonora

Reference: TIN2009-14247-C02-02
Funding: Ministerio de Ciencia e Innovación
Period: from 01/01/2010 to 31/12/2013
Project Leader: Iñesta Quereda, José Manuel

Summary of the project:

A key challenge in the area of music information, given the explosion of online music and the rapidly expanding digital music collections, is the development of efficient and reliable tools for music description, search and retrieval. Conventional music description, search and retrieval systems are mainly based on text metadata. However, music contents and text contents are of a very different nature which very often makes textual information retrieval unsatisfactory in a musical context. The overall aim of the proposed project is to study and develop innovative components for music description and information retrieval systems. The key feature is the usage and exploitation of semantic descriptors of musical content which are automatically extracted from music data. For that, the use of pattern recognition and machine learning techniques is a basic tool. Nowadays, pattern recognition applications whose solutions have a sequential nature, like machine translation, speech recognition, etc. are conceived to work off-line. Recently, to involve this supervision stage in the system's learning is receiving a growing interest. This way, through the use of an interactive interface the system can improve its models from the user's corrections, improving its performance and preventing from future errors. This approach is applicable in the present project to tasks like music transcription and tonal analysis. Specifically, the main objectives of the project are: 1. Extraction, analysis and processing of low-level descriptors from both symbolic music and digital audio. The spectral modeling analysis and synthesis techniques previously developed by the Music Technology Group at University Pompeu Fabra (MTG-UPF) will be used for this purpose. Also the background on symbolic sequence analysis by the grupo de Reconocimiento de Formas e Inteligencia Artificial at University of Alicante (gRFIA-UA) group will be applied here. 2. High-level musical semantic attribute extraction (capable of describe similarity, music categories, expressiveness and musical structure), based on the low-level descriptors from the previous point. 3. Design and implementation of pattern recognition and machine learning techniques for building semantic models of different aspects of music and sound. The models will involve techniques to deal with this multimodal aspect of the multimedia content. 4. Development of prototype systems for music mining, study, personalization, and information retrieval. Some of these prototypes will be designed under an interactive approach, where the feedback from the user expert can help to improve the underlying models.

Departament of Software and Computing Systems

University of Alicante, carretera San Vicente s/n

03690 San Vicente del Raspeig, Alicante (Spain)

Tel: (+34) 96 590 3772

Follow us on:

[Twitter] [Facebook]