Detection and Classification of Acoustic Scenes and Events: Outcome of the DCASE 2016 Challenge

By Annamaria Mesaros, Toni Heittola, Emmanouil Benetos, Peter Foster, Mathieu Lagrange, Tuomas Virtanen, Mark D. Plumbley. 2018

313 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Signal Processing

Citations in the corpus

Speech Denoising with Deep Feature Losses (2018, methodology): “) We use two tasks from the DCASE 2016 challenge [35]: the acoustic scene classification task and the domestic audio tagging task.”
FSD50K: An Open Dataset of Human-Labeled Sound Events (2020, background): “The SER research community has grown substantially over the last decade, as evidenced by the increasing traction of the Detection and Classiﬁcation of Acoustic Scenes and Events (DCASE) Challenge and Workshop [13], which promote research and evaluation on common publicly available datasets.”
PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition (2019, background): “Recently, the Detection and Classification of Acoustic Scenes and Events (DCASE) challenge series since 2013 [8], [9], [10], [2] have provided publicly available datasets including acoustic scene classification and sound event detection datasets for researchers to use.”
An Active Learning Method Using Clustering and Committee-Based Sample Selection for Sound Event Classification (2018, background): “Sound event classification [1, 2] has many applications such as environmental noise monitoring [3], road surveillance [4] and remote health care [5].”
General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline (2018, methodology): “In DCASE 2016 [3], the task targeted domestic audio tagging for which the CHiME-Home dataset was used, including 7 sound categories and 6.”
A Framework for the Robust Evaluation of Sound Event Detection (2019, background): “The notion of collars introduced in [9,10] and deployed in DCASE [4, 5, 7, 8] considers that a ground truth event for class c, yi ∈ Yc is correctly detected as a TP if the following condition is satisfied: ∃xj ∈ X ∗ c such that (ts,i − tc) ≤ ts,j ≤ (ts,i + tc) AND (te,i − t̄c) ≤ te,j ≤ (te,i + t̄c) ”
MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection (2019, background): “Remarkable advancements have been made in the classiﬁcation of acoustic scenes and the detection of acoustic events, and there are many promising state-of-the-art studies in this vein [14–16].”
A Deep Residual Network for Large-Scale Acoustic Scene Analysis (2019, background): “There has been a lot of progress thanks to many publicly available datasets, such as ESC, those in the DCASE challenges, and AudioSet [7, 8, 9, 10].”
A multi-device dataset for urban acoustic scene classification (2018, methodology): “In the first three editions of the challenge, the acoustic scene classification task has received the highest number of submissions among the available tasks, with 17 submissions in 2013 [1], 48 submissions in 2016 [2], and 97 submissions in 2017 [3].”
The Benefit of Temporally-Strong Labels in Audio Event Classification (2021, background): “Datasets incorporating strong labels appeared with the first editions of the DCASE Challenge [2].”
BirdNET: A deep learning solution for avian diversity monitoring (2021, background): “3 from the Freefield1010 (Stowell and Plumbley, 2013) and WarblR datasets, which are both part of the DCASE bird detection challenge and did not contain bird sounds (Mesaros et al., 2018; Stowell et al., 2016).”