Semi-Supervised Active Learning for Sound Classification in Hybrid Learning Environments

By Wenjing Han, Eduardo Coutinho, Huabin Ruan, Haifeng Li, Björn Schuller, Xiaojie Yu, Xuan Zhu. 2016

65 citations recorded by the source corpus.

Coping with scarcity of labeled data is a common problem in sound classification tasks. Approaches for classifying sounds are commonly based on supervised learning algorithms, which require labeled data which is often scarce and leads to models that do not generalize well. In this paper, we make an efficient combination of confidence-based Active Learning and Self-Training with the aim of minimizing the need for human annotation for sound classification model training. The proposed method pre-processes the instances that are ready for labeling by calculating their classifier confidence scores, and then delivers the candidates with lower scores to human annotators, and those with high scores are automatically labeled by the machine. We demonstrate the feasibility and efficacy of this method in two practical scenarios: pool-based and stream-based processing. Extensive experimental results indicate that our approach requires significantly less labeled instances to reach the same performance in both scenarios compared to Passive Learning, Active Learning and Self-Training. A reduction of 52.2% in human labeled instances is achieved in both of the pool-based and stream-based scenarios on a sound classification task considering 16,930 sound instances.

Subfields: Civil and Structural Engineering, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Civil and Structural Engineering

In Signal Processing

Citations in the corpus

FSD50K: An Open Dataset of Human-Labeled Sound Events (2020, background): “Recent works studying AL for SER [52]–[55] report reduced annotation effort with good performance which, in principle, makes AL appealing for dataset creation.”
An Active Learning Method Using Clustering and Committee-Based Sample Selection for Sound Event Classification (2018, methodology): “SSAL [11] is used as the second reference method.”
DCASE2017 Challenge Setup: Tasks, Datasets and Baseline System (2017, background): “Current literature has shown potential using unsupervised [18, 19, 20] and semi-supervised approaches [21, 22] some of them employing weak labels [23].”
Learning Sound Event Classifiers from Web Audio with Noisy Labels (2019, background): “Some work focuses on self-training to learning from combinations of labeled and unlabeled data [7, 8, 9], but the issue of label noise is not addressed per se.”
Active Learning for Efficient Audio Annotation and Classification with a Large Amount of Unlabeled Data (2019, methodology): “Previous works have demonstrated the benefit of using AL combined with semi-supervised learning (SSL) [18, 19], a technique that uses a pre-trained model on a smaller set of labeled data to automatically annotate a larger set of unlabeled data.”