Self-supervised Attention Model for Weakly Labeled Audio Event Classification

08/07/2019
by   Bongjun Kim, et al.
0

We describe a novel weakly labeled Audio Event Classification approach based on a self-supervised attention model. The weakly labeled framework is used to eliminate the need for expensive data labeling procedure and self-supervised attention is deployed to help a model distinguish between relevant and irrelevant parts of a weakly labeled audio clip in a more effective manner compared to prior attention models. We also propose a highly effective strongly supervised attention model when strong labels are available. This model also serves as an upper bound for the self-supervised model. The performances of the model with self-supervised attention training are comparable to the strongly supervised one which is trained using strong labels. We show that our self-supervised attention method is especially beneficial for short audio events. We achieve 8.8 over the current state-of-the-art systems for SL-DCASE-17 and balanced AudioSet.

READ FULL TEXT
research
09/28/2022

Audio Barlow Twins: Self-Supervised Audio Representation Learning

The Barlow Twins self-supervised learning objective requires neither neg...
research
05/25/2023

Perturbation-based Self-supervised Attention for Attention Bias in Text Classification

In text classification, the traditional attention mechanisms usually foc...
research
06/23/2023

Bring Your Own Data! Self-Supervised Evaluation for Large Language Models

With the rise of Large Language Models (LLMs) and their ubiquitous deplo...
research
11/06/2020

ControlFlag: A Self-supervised Idiosyncratic Pattern Detection System for Software Control Structures

Software debugging has been shown to utilize upwards of 50 time. Machine...
research
10/25/2019

SPICE: Self-supervised Pitch Estimation

We propose a model to estimate the fundamental frequency in monophonic a...
research
11/17/2022

Balanced Deep CCA for Bird Vocalization Detection

Event detection improves when events are captured by two different modal...
research
10/09/2021

Visually Exploring Multi-Purpose Audio Data

We analyse multi-purpose audio using tools to visualise similarities wit...

Please sign up or login with your details

Forgot password? Click here to reset