A Closer Look at Weak Label Learning for Audio Events

By Ankit Shah, Anurag Kumar, Alexander G. Hauptmann, Bhiksha Raj. 2018

70 citations recorded by the source corpus.

Audio content analysis in terms of sound events is an important research problem for a variety of applications. Recently, the development of weak labeling approaches for audio or sound event detection (AED) and availability of large scale weakly labeled dataset have finally opened up the possibility of large scale AED. However, a deeper understanding of how weak labels affect the learning for sound events is still missing from literature. In this work, we first describe a CNN based approach for weakly supervised training of audio events. The approach follows some basic design principle desirable in a learning method relying on weakly labeled audio. We then describe important characteristics, which naturally arise in weakly supervised learning of sound events. We show how these aspects of weak labels affect the generalization of models. More specifically, we study how characteristics such as label density and corruption of labels affects weakly supervised training for audio events. We also study the feasibility of directly obtaining weak labeled data from the web without any manual label and compare it with a dataset which has been manually labeled. The analysis and understanding of these factors should be taken into picture in the development of future weak label learning methods. Audioset, a large scale weakly labeled dataset for sound events is used in our experiments.

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): “The longer the clips, the higher the the so-called label density noise [77]”
Cross Modal Audio Search and Retrieval with Joint Embeddings Based on Text and Audio (2019, methodology): “We used two types of audio features: standard Melfrequency cepstral coefficients (MFCCs) and state-of-the-art Walnet features [16, 17].”
Compression of Acoustic Event Detection Models With Quantized Distillation (2019, background): “It can also enhance humancomputer interaction by providing context-related information [2].”
Sound Event Detection in Domestic Environments with Weakly Labeled Data and Soundscape Synthesis (2019, unknown): “Sound event detection (SED) systems trained using weak labels have have seen signiﬁcant interest [6, 9, 10, 11, 12] in the research community, as they address some of the challenges involved in developing models that require strongly labeled data for training.”
SeCoST: Sequential Co-Supervision for Weakly Labeled Audio Event Detection (2019, methodology): “We use a deep convolutional neural network as the pro-totypical learning model that drives our proposed framework [10], [25].”
Addressing Missing Labels in Large-Scale Sound Event Recognition Using a Teacher-Student Framework With Loss Masking (2020, background): “Previous work analyses the impact of label noise in these tasks [9, 10], as well as proposes ways to mitigate its negative effect [11, 12, 13, 14].”
Learning Sound Event Classifiers from Web Audio with Noisy Labels (2019, methodology): “In [10], the effect of label noise on weakly supervised learning was analyzed by introducing noise to AudioSet.”