Sound Event Detection from Partially Annotated Data: Trends and Challenges

Romain Serizel 1 Nicolas Turpault 1
1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : This paper proposes an overview of the latest advances and challenges in sound event detection and classification with systems trained on partially annotated data. The paper fo-cuses on the scientific aspects highlighted by the task 4 of DCASE 2018 challenge: large-scale weakly labeled semi-supervised sound event detection in domestic environments. Given a small training set composed of weakly labeled audio clips (without timestamps) and a larger training set composed of unlabeled audio clips, the target of the task is to provide not only the event class but also the event time boundaries given that multiple events can be present in an audio clip. This paper proposes a detailed analysis of the impact of the time segmentation, the event classification and the methods used to exploit unlabeled data on the final performance of sound event detection systems.
Complete list of metadatas

Cited literature [29 references]  Display  Hide  Download

https://hal.inria.fr/hal-02114652
Contributor : Romain Serizel <>
Submitted on : Wednesday, May 1, 2019 - 11:35:54 AM
Last modification on : Friday, May 17, 2019 - 10:31:25 AM

File

IcETRAN2019.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02114652, version 2

Collections

Citation

Romain Serizel, Nicolas Turpault. Sound Event Detection from Partially Annotated Data: Trends and Challenges. IcETRAN conference, Jun 2019, Srebrno Jezero, Serbia. ⟨hal-02114652v2⟩

Share

Metrics

Record views

82

Files downloads

431