Lexical and Perceptual Grounding of a Sound Ontology

Sound ontologies need to incorporate source unidentifiable sounds in an adequate and consistent manner. Computational lexical resources like WordNet have either inserted these descriptions into conceptual categories, or make no attempt to organize the terms for these sounds. This work attempts to add structure to linguistic terms for source unidentifiable sounds. Through an analysis of WordNet and a psychoacoustic experiment we make some preliminary proposal about which features are highly salient for sound classification. This work is essential for interfacing between source unidentifiable sounds and linguistic descriptions of those sounds in computational applications, such as the Semantic Web and robotics. Key words: Ontology, source unidentifiable sounds, sound features, WordNet, psycho-acoustic experiment 1 Sounds without Identifiable Sources Bumps, rattles and rumbles: languages are filled with expressions to name sounds that we cannot identify according to their origin, t...

• Type: Conference
• Year: 2007
• Where: TSD
• Authors: Anna Lobanova, Jennifer Spenader, Bea Valkenier
• Keywords: Ontologies, Signal Processing, Source Identifiable Sound, Source Unidentifiable Sounds, TSD 2007