Wikitag: Wikipedia-Based Knowledge Embeddings Towards Improved Acoustic Event Classification
Lists
Only you see this
Abstract
Acoustic event classification (AEC) is the task of determining whether certain events occur in an audio clip. Inspired by previous research [1], [2], [3] that embeddings from event labels can be leveraged to facilitate the learning of new detectors with no or limited audio samples, we introduce Wikipedia-based text embeddings as auxiliary information to improve AEC. We describe how to extract label embeddings from multiple Wikipedia texts, and formulate the multi-view aligned AEC problem based on VGGish model. We show that our "wikiTAG" embeddings encode rich semantic information and are more informative than label embeddings for AEC tasks. Compared to a supervised baseline on AudioSet, the multi-view model with "wikiTAG" embeddings achieves 7.3% and 1.3% relative improvement in mean average precision (mAP) using 10% and full AudioSet for training, respectively. To the author’s knowledge, this is the first work in the AEC domain on building large-scale label representations by leveraging Wikipedia data in a systematic fashion.
BibTeX
@inproceedings{zhang2022wikitag,
author = {Qin Zhang and Qingming Tang and Chieh-Chi Kao and Ming Sun and Yang Liu and Chao Wang},
title = {{Wikitag: Wikipedia-Based Knowledge Embeddings Towards Improved Acoustic Event Classification}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2022},
url = {https://openreview.net/forum?id=OcWh0aHiMRT},
}Loading related content...