Supervised hierarchical segmentation for bird song recording
Teresa Vania Tjahja, Xiaoli Z. Fern, Raviv Raich, Anh T. Pham
Abstract
A common framework of identifying bird species from audio recordings involves detecting bird song segments, which will be subsequently input to a classifier. In-field recordings are contaminated with various environmental noise. For such recordings, supervised segmentation has been observed to outperform unsupervised energy-based approaches. Prior supervised segmentation work considers only pixel-level predictions and ignores the supervision provided at the segment-level. We propose a hierarchical approach that learns to isolate bird song syllables based on both pixel-level and segment-level information. Experimental results suggest that our method outperforms an existing supervised method that learns only from pixel-level supervision.
BibTeX
@inproceedings{icassp2015_supervisedhierar,
title = {Supervised hierarchical segmentation for bird song recording},
author = {Teresa Vania Tjahja and Xiaoli Z. Fern and Raviv Raich and Anh T. Pham},
booktitle = {ICASSP 2015},
year = {2015}
}