-
Learning Sound Event Classifiers from Web Audio with Noisy Labels
As sound event classification moves towards larger datasets, issues of l...
read it
-
Learning from Noisy Labels with Noise Modeling Network
Multi-label image classification has generated significant interest in r...
read it
-
Iteratively Learning from the Best
We study a simple generic framework to address the issue of bad training...
read it
-
Investigating Label Noise Sensitivity of Convolutional Neural Networks for Fine Grained Audio Signal Labelling
We measure the effect of small amounts of systematic and random label no...
read it
-
On the Resistance of Neural Nets to Label Noise
We investigate the behavior of convolutional neural networks (CNN) in th...
read it
-
Exploratory Machine Learning with Unknown Unknowns
In conventional supervised learning, a training dataset is given with gr...
read it
-
Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise
The growing importance of massive datasets with the advent of deep learn...
read it
Supervised Classifiers for Audio Impairments with Noisy Labels
Voice-over-Internet-Protocol (VoIP) calls are prone to various speech impairments due to environmental and network conditions resulting in bad user experience. A reliable audio impairment classifier helps to identify the cause for bad audio quality. The user feedback after the call can act as the ground truth labels for training a supervised classifier on a large audio dataset. However, the labels are noisy as most of the users lack the expertise to precisely articulate the impairment in the perceived speech. In this paper, we analyze the effects of massive noise in labels in training dense networks and Convolutional Neural Networks (CNN) using engineered features, spectrograms and raw audio samples as inputs. We demonstrate that CNN can generalize better on the training data with a large number of noisy labels and gives remarkably higher test performance. The classifiers were trained both on randomly generated label noise and the label noise introduced by human errors. We also show that training with noisy labels requires a significant increase in the training dataset size, which is in proportion to the amount of noise in the labels.
READ FULL TEXT
Comments
There are no comments yet.