Learning to Detect Novel and Fine-Grained Acoustic Sequences Using Pretrained Audio Representations

Autor:	Kowtha, Vasudha, Marques, Miquel Espi, Huang, Jonathan, Zhang, Yichi, Avendano, Carlos
Rok vydání:	2023
Předmět:	Computer Science - Sound Computer Science - Machine Learning Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	This work investigates pretrained audio representations for few shot Sound Event Detection. We specifically address the task of few shot detection of novel acoustic sequences, or sound events with semantically meaningful temporal structure, without assuming access to non-target audio. We develop procedures for pretraining suitable representations, and methods which transfer them to our few shot learning scenario. Our experiments evaluate the general purpose utility of our pretrained representations on AudioSet, and the utility of proposed few shot methods via tasks constructed from real-world acoustic sequences. Our pretrained embeddings are suitable to the proposed task, and enable multiple aspects of our few shot framework. Comment: IEEE ICASSP 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.02382 Zobrazit plný text záznamu View this record from Arxiv