Audio Tagging by Cross Filtering Noisy Labels

by   Boqing Zhu, et al.

High quality labeled datasets have allowed deep learning to achieve impressive results on many sound analysis tasks. Yet, it is labor-intensive to accurately annotate large amount of audio data, and the dataset may contain noisy labels in the practical settings. Meanwhile, the deep neural networks are susceptive to those incorrect labeled data because of their outstanding memorization ability. In this paper, we present a novel framework, named CrossFilter, to combat the noisy labels problem for audio tagging. Multiple representations (such as, Logmel and MFCC) are used as the input of our framework for providing more complementary information of the audio. Then, though the cooperation and interaction of two neural networks, we divide the dataset into curated and noisy subsets by incrementally pick out the possibly correctly labeled data from the noisy data. Moreover, our approach leverages the multi-task learning on curated and noisy subsets with different loss function to fully utilize the entire dataset. The noisy-robust loss function is employed to alleviate the adverse effects of incorrect labels. On both the audio tagging datasets FSDKaggle2018 and FSDKaggle2019, empirical results demonstrate the performance improvement compared with other competing approaches. On FSDKaggle2018 dataset, our method achieves state-of-the-art performance and even surpasses the ensemble models.


page 1

page 2

page 10


Audio tagging with noisy labels and minimal supervision

This paper introduces Task 2 of the DCASE2019 Challenge, titled "Audio t...

General audio tagging with ensembling convolutional neural network and statistical features

Audio tagging aims to infer descriptive labels from audio clips. Audio t...

A Simple yet Effective Baseline for Robust Deep Learning with Noisy Labels

Recently deep neural networks have shown their capacity to memorize trai...

The Impact of Label Noise on a Music Tagger

We explore how much can be learned from noisy labels in audio music tagg...

Joint Negative and Positive Learning for Noisy Labels

Training of Convolutional Neural Networks (CNNs) with data with noisy la...

Balanced Symmetric Cross Entropy for Large Scale Imbalanced and Noisy Data

Deep convolution neural network has attracted many attentions in large-s...

Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion

Deep neural networks need large amounts of labeled data to achieve good ...

Please sign up or login with your details

Forgot password? Click here to reset