Title :
Unsupervised hierarchical structure induction for deeper semantic analysis of audio
Author :
Chaudhuri, Swarat ; Raj, Bhiksha
Author_Institution :
Language Technol. Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
Current audio analysis techniques rely on fairly shallow analysis of audio content, using symbols or patterns extracted directly from the observed acoustics. We hypothesize that the observed acoustics actually map to semantics in a hierarchical manner, and that the higher levels of this hierarchy correspond to increasingly higher-level semantics. In this paper, we present a model for deeper analysis of the observed acoustics, that induces a probabilistic tree structure depending on estimated constituent identities and contexts. Audio characterization using the deeper structure outperforms the standard shallow-feature based characterizations.
Keywords :
audio acoustics; audio signal processing; probability; audio analysis technique; audio characterization; deeper semantic analysis; pattern extraction; probabilistic tree structure; symbol extraction; unsupervised hierarchical structure induction; Acoustics; Analytical models; Context; Estimation; Grammar; Semantics; Vegetation; automatic content analysis; semantic audio; structure discovery; unsupervised learning;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
Conference_Location :
Vancouver, BC
DOI :
10.1109/ICASSP.2013.6637765