Sound Event Detection with Adaptive Frequency Selection

05/17/2021
by   Zhepei Wang, et al.
0

In this work, we present HIDACT, a novel network architecture for adaptive computation for efficiently recognizing acoustic events. We evaluate the model on a sound event detection task where we train it to adaptively process frequency bands. The model learns to adapt to the input without requesting all frequency sub-bands provided. It can make confident predictions within fewer processing steps, hence reducing the amount of computation. Experimental results show that HIDACT has comparable performance to baseline models with more parameters and higher computational complexity. Furthermore, the model can adjust the amount of computation based on the data and computational budget.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/29/2018

Learning How to Listen: A Temporal-Frequential Attention Model for Sound Event Detection

In this paper, we propose a temporal-frequential attention model for sou...
research
03/29/2019

Multi-Scale Time-Frequency Attention for Rare Sound Event Detection

Attention mechanism has been widely applied to various sound-related tas...
research
11/15/2019

Adaptive Multi-scale Detection of Acoustic Events

The goal of acoustic (or sound) events detection (AED or SED) is to pred...
research
10/30/2018

SubSpectralNet - Using Sub-Spectrogram based Convolutional Neural Networks for Acoustic Scene Classification

Acoustic Scene Classification (ASC) is one of the core research problems...
research
02/02/2019

Sound Event Detection Using Graph Laplacian Regularization Based on Event Co-occurrence

The types of sound events that occur in a situation are limited, and som...
research
06/20/2023

Frequency Channel Attention for computationally efficient sound event detection

We explore on various attention methods on frequency and channel dimensi...
research
02/18/2023

Multi-dimensional frequency dynamic convolution with confident mean teacher for sound event detection

Recently, convolutional neural networks (CNNs) have been widely used in ...

Please sign up or login with your details

Forgot password? Click here to reset