AudioNet: Supervised Deep Hashing for Retrieval of Similar Audio Events

TL;DR

AudioNet introduces a supervised deep hashing approach for efficient retrieval of similar audio events, achieving high performance and setting new benchmarks through a novel loss function and discrete gradient propagation.

Contribution

The paper presents a novel deep hashing method with a new loss function and discrete gradient propagation for improved audio event retrieval performance.

Findings

High retrieval accuracy on multiple datasets

Effective handling of imbalanced datasets

Establishes a new benchmark in audio retrieval

Abstract

This work presents a supervised deep hashing method for retrieving similar audio events. The proposed method, named AudioNet, is a deep-learning-based system for efficient hashing and retrieval of similar audio events using an audio example as a query. AudioNet achieves high retrieval performance on multiple standard datasets by generating binary hash codes for similar audio events, setting new benchmarks in the field, and highlighting its efficacy and effectiveness compare to other hashing methods. Through comprehensive experiments on standard datasets, our research represents a pioneering effort in evaluating the retrieval performance of similar audio events. A novel loss function is proposed which incorporates weighted contrastive and weighted pairwise loss along with hashcode balancing to improve the efficiency of audio event retrieval. The method adopts discrete gradient propagation, which allows gradients to be propagated through discrete variables during backpropagation. This enables the network to optimize the discrete hash codes using standard gradient-based optimization algorithms, which are typically used for continuous variables. The proposed method showcases promising retrieval performance, as evidenced by the experimental results, even when dealing with imbalanced datasets. The systematic analysis conducted in this study further supports the significant benefits of the proposed method in retrieval performance across multiple datasets. The findings presented in this work establish a baseline for future studies on the efficient retrieval of similar audio events using deep audio embeddings.