Learn More
We propose the method of independent subspace analysis (ISA) for separating individual audio sources from a single-channel mixture. ISA is based on independent component analysis (ICA) but relaxes the constraint that requires at least as many mixture observation signals as sources. A second extension to ICA is the use of dynamic components to represent(More)
Current retrieval systems can handle tens-of-thousands of music tracks but new systems need to aim at huge online music collections that contain tens-of-millions of tracks. ABSTRACT | The steep rise in music downloading over CD sales has created a major shift in the music industry away from physical media formats and towards online products and services.(More)
We propose an automatic method for measuring content-based music similarity, enhancing the current generation of music search engines and recommended systems. Many previous approaches to track similarity require brute-force, pair-wise processing between all audio features in a database and therefore are not practical for large collections. However, in an(More)
• General audio consists of a wide range of sound phenomena such as music, sound effects, • Au: In TOC the chapter title is given as Sound Classification, please clarify. • Au: Please provide affiliation details. environmental sounds, speech and nonspeech utterances. The sound recognition tools provide a means for classifying and querying such diverse audio(More)
We investigate explicit segment duration models in addressing the problem of fragmentation in musical audio segmentation. The resulting probabilistic models are optimised using Markov Chain Monte Carlo methods; in particular, we introduce a modification to Wolff’s algorithm to make it applicable to a segment classification model with an arbitrary duration(More)
We propose a method for automatic fine-scale audio description that draws inspiration from ontological sound description methods such as Shaeffer's Objets Sonores and Smalley's Spectromorphology. Our goal is complete automation of audio description at the level of sound objects for indexing and retrieving sound segments within Internet audio documents. To(More)
We describe an algorithm for finding approximate sequence similarity at all scales of interest, being explicit about our modelling assumptions and the parameters of the algorithm. We further present an algorithm for producing section labels based on the sequence similarity, and compare these labels with some expert-provided ground truth for a particular set(More)
OBJECTIVE To assess adolescents' perceptions about factors influencing their food choices and eating behaviors. DESIGN Data were collected in focus-group discussions. SUBJECTS/SETTING The study population included 141 adolescents in 7th and 10th grade from 2 urban schools in St Paul, Minn, who participated in 21 focus groups. ANALYSIS Data were(More)
A method for segmenting musical audio with a hierarchical timbre model is introduced. New evidence is presented to show that music segmentation can be recast as clustering of timbre features, and a new clustering algorithm is described. A prototype thumbnail-generating application is described and evaluated. Experimental results are given, including(More)