Corpus ID: 211082815

Active Learning for Sound Event Detection

@article{Zhao2020ActiveLF,
  title={Active Learning for Sound Event Detection},
  author={Shuyang Zhao and Toni Heittola and Tuomas Virtanen},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.05033}
}
  • Shuyang Zhao, Toni Heittola, Tuomas Virtanen
  • Published in ArXiv 2020
  • Computer Science, Engineering, Mathematics
  • This paper proposes an active learning system for sound event detection (SED). It aims at maximizing the accuracy of a learned SED model with limited annotation effort. The proposed system analyzes an initially unlabeled audio dataset, from which it selects sound segments for manual annotation. The candidate segments are generated based on a proposed change point detection approach, and the selection is based on the principle of mismatch-first farthest-traversal. During the training of SED… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES

    An Active Learning Method Using Clustering and Committee-Based Sample Selection for Sound Event Classification

    VIEW 4 EXCERPTS

    Large-Scale Weakly Supervised Audio Classification Using Gated Convolutional Neural Network

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Audio Set: An ontology and human-labeled dataset for audio events

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Weakly Labelled AudioSet Tagging With Attention Neural Networks

    A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling

    VIEW 1 EXCERPT

    Knowledge Transfer from Weakly Labeled Audio Using Convolutional Neural Network for Sound Events and Scenes

    VIEW 3 EXCERPTS