A Morphological Model for Simulating Acoustic Scenes and Its Application to Sound Event Detection

Self Cite

263

159

Public evaluation campaigns and datasets promote\ud active development in target research areas, allowing direct\ud comparison of algorithms. The second edition of the challenge\ud on Detection and Classification of Acoustic Scenes and Events\ud (DCASE 2016) has offered such an opportunity for development\ud of state-of-the-art methods, and succeeded in drawing together a\ud large number of participants from academic and industrial backgrounds.\ud In this paper, we report on the tasks and outcomes of\ud the DCASE 2016 challenge. The challenge comprised four tasks:\ud acoustic scene classification, sound event detection in synthetic\ud audio, sound event detection in real-life audio, and domestic\ud audio tagging. We present in detail each task and analyse the\ud submitted systems in terms of design and performance. We\ud observe the emergence of deep learning as the most popular\ud classification method, replacing the traditional approaches based\ud on Gaussian mixture models and support vector machines. By\ud contrast, feature representations have not changed substantially\ud throughout the years, as mel frequency-based representations\ud predominate in all tasks. The datasets created for and used in\ud DCASE 2016 are publicly available and are a valuable resource\ud for further research

Section: A Dataset and Experimental Setupmentioning

confidence: 99%

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

Mesaros

Heittola

Benetos

et al. 2018

Self Cite

263

159

“…One challenge in this is that these mixtures should be created such that they mimic real-life data, and this is not trivial. Until now, the synthetic data used in DCASE tasks was rather simplisticfor example the DCASE 2016 Task 2 synthetic audio dataset used a morphological model for creating the mixtures [50], but it was based on a very small number of event instances, while this year's Task 2 rare sound events dataset did not use any specific knowledge or rules for background and target event combinations.…”

Section: I C O N C L U S I O N Smentioning

confidence: 99%

Sound Event Detection in the DCASE 2017 Challenge

Mesaros

Diment

Elizalde

et al. 2019

114

Each edition of the challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) contained several tasks involving sound event detection in different setups. DCASE 2017 presented participants with three such tasks, each having specific datasets and detection requirements: Task 2, in which target sound events were very rare in both training and testing data, Task 3 having overlapping events annotated in real-life audio, and Task 4, in which only weakly-labeled data was available for training. In this paper, we present the three tasks, including the datasets and baseline systems, and analyze the challenge entries for each task. We observe the popularity of methods using deep neural networks, and the still widely used mel frequency based representations, with only few approaches standing out as radically different. Analysis of the systems behavior reveals that task-specific optimization has a big role in producing good performance; however, often this optimization closely follows the ranking metric, and its maximization/minimization does not result in universally good performance. We also introduce the calculation of confidence intervals based on a jackknife resampling procedure, to perform statistical analysis of the challenge results. The analysis indicates that while the 95% confidence intervals for many systems overlap, there are significant difference in performance between the top systems and the baseline for all tasks.

“…The dataset, denoted 'OS test', contains 12 recordings of 2 minutes duration each, with different event density levels and different event-to-background ratio levels. The recordings were generated using the acoustic scene synthesizer of [31] by concatenating isolated office sounds recorded at Queen Mary University of London (using different sound sources than the ones used for the OS development dataset of subsection IV-A). This polyphonic dataset allows for direct comparison with other participating systems for the DCASE 2013 polyphonic event detection task.…”

Section: B Test Datamentioning

confidence: 99%

Polyphonic Sound Event Tracking Using Linear Dynamical Systems

Benetos

Lafay

Lagrange

et al. 2017

Self Cite

Abstract-In this paper, a system for polyphonic sound event detection and tracking is proposed, based on spectrogram factorisation techniques and state space models. The system extends probabilistic latent component analysis (PLCA) and is modelled around a 4-dimensional spectral template dictionary of frequency, sound event class, exemplar index, and sound state. In order to jointly track multiple overlapping sound events over time, the integration of linear dynamical systems (LDS) within the PLCA inference is proposed. The system assumes that the PLCA sound event activation is the (noisy) observation in an LDS, with the latent states corresponding to the true event activations. LDS training is achieved using fully observed data, making use of ground truth-informed event activations produced by the PLCA-based model. Several LDS variants are evaluated, using polyphonic datasets of office sounds generated from an acoustic scene simulator, as well as real and synthesized monophonic datasets for comparative purposes. Results show that the integration of LDS tracking within PLCA leads to an improvement of +8.5-10.5% in terms of frame-based F-measure as compared to the use of the PLCA model alone. In addition, the proposed system outperforms several state-of-the-art methods for the task of polyphonic sound event detection.