Tuyển tập báo cáo các nghiên cứu khoa học quốc tế ngành hóa học dành cho các bạn yêu hóa học tham khảo đề tài: Research Article Ecological Acoustics Perspective for Content-Based Retrieval of Environmental Sounds | Hindawi Publishing Corporation EURASIP Journal on Audio Speech and Music Processing Volume 2010 Article ID 960863 11 pages doi 2010 960863 Research Article Ecological Acoustics Perspective for Content-Based Retrieval of Environmental Sounds Gerard Roma Jordi Janer Stefan Kersten Mattia Schirosa Perfecto Herrera and Xavier Serra Music Technology Group Universitat Pompeu Fabra Roc Boronat 138 08018 Barcelona Spain Correspondence should be addressed to Gerard Roma Received 1 March 2010 Accepted 22 November 2010 Academic Editor Andrea Valle Copyright 2010 Gerard Roma et al. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use distribution and reproduction in any medium provided the original work is properly cited. In this paper we present a method to search for environmental sounds in large unstructured databases of user-submitted audio using a general sound events taxonomy from ecological acoustics. We discuss the use of Support Vector Machines to classify sound recordings according to the taxonomy and describe two use cases for the obtained classification models a content-based web search interface for a large audio database and a method for segmenting field recordings to assist sound design. 1. Introduction Sound designers have traditionally made extensive use of recordings for creating the auditory content of audiovisual productions. Many of these sound effects come from commercial sound libraries either in the form of CD DVD collections or more recently as online databases. These repositories are organized according to editorial criteria and contain a wide range of sounds recorded in controlled environments. With the rapid growth of social media large amounts of sound material are becoming available through the web every day. In contrast with traditional audiovisual media networked multimedia environments can exploit such a rich source of data to provide content that .
