Comparative Assessment of Data Augmentation for Semi-Supervised Polyphonic Sound Event Detection

Delphin-Poulat, Lionel; Nicol, Rozenn; Plapous, Cyril; Peron, Katell

doi:10.23919/fruct49677.2020.9211023

Cited by 6 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine Learning). In future works, we want to explore this possibility by using Artificial Neural Networks such as those used in [13]. In addition, localization of infrasound events will be examined by using a sensor array.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Recording and Analyzing Infrasounds to Monitor Human Activities in Buildings

Nicol,

Plapous,

Avenel

et al. 2024

Proceedings of the 10th Convention of the European Acoustics Association Forum Acusticum 2023

View full text Add to dashboard Cite

Infrasound waves originate from multiple sources, whether anthropogenic (explosion) or natural (earthquake, volcano, storm, etc.). They are generally used in atmospheric physics and to monitor nuclear weapons. People familiar with infrasound measurement also know that human presence and activities in buildings (moving, passing through a door, opening a window, use of machines, etc.) produce infrasounds. In the context of smart buildings, these infrasounds may be detected and analyzed to infer information. Infrasounds have the advantages of propagating over long distances and circumventing obstacles. For this reason, a few sensors are able to monitor a large area, but in counterpart recordings may be contaminated by undesired sources.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Recording and Analyzing Infrasounds to Monitor Human Activities in Buildings

Nicol,

Plapous,

Avenel

et al. 2024

Proceedings of the 10th Convention of the European Acoustics Association Forum Acusticum 2023

View full text Add to dashboard Cite

show abstract

“…On the other hand, source separation algorithms aim to extract the underlying events or different audio sources in a segment [41,42], thus reducing event overlap before the event detection system. Both Mixup and source separation have already been explored to increase the performance of SED in the DCASE evaluation [43,44], however, the impact of these techniques in highly overlapped scenarios has not been explicitly assessed yet.…”

Section: Eventmentioning

confidence: 99%

An Analysis of Sound Event Detection under Acoustic Degradation Using Multi-Resolution Systems

2021

View full text Add to dashboard Cite

The Sound Event Detection task aims to determine the temporal locations of acoustic events in audio clips. In recent years, the relevance of this field is rising due to the introduction of datasets such as Google AudioSet or DESED (Domestic Environment Sound Event Detection) and competitive evaluations like the DCASE Challenge (Detection and Classification of Acoustic Scenes and Events). In this paper, we analyze the performance of Sound Event Detection systems under diverse artificial acoustic conditions such as high- or low-pass filtering and clipping or dynamic range compression, as well as under an scenario of high overlap between events. For this purpose, the audio was obtained from the Evaluation subset of the DESED dataset, whereas the systems were trained in the context of the DCASE Challenge 2020 Task 4. Our systems are based upon the challenge baseline, which consists of a Convolutional-Recurrent Neural Network trained using the Mean Teacher method, and they employ a multiresolution approach which is able to improve the Sound Event Detection performance through the use of several resolutions during the extraction of Mel-spectrogram features. We provide insights on the benefits of this multiresolution approach in different acoustic settings, and compare the performance of the single-resolution systems in the aforementioned scenarios when using different resolutions. Furthermore, we complement the analysis of the performance in the high-overlap scenario by assessing the degree of overlap of each event category in sound event detection datasets.

show abstract

Semi-Supervised NMF-CNN for Sound Event Detection

Chan

Chin

2021

IEEE Access

View full text Add to dashboard Cite

The lack of strongly labeled data can limit the potential of a Sound Event Detection (SED) system trained using deep learning approaches. To address this issue, this paper proposes a novel method to approximate strong labels for the weakly labeled data using Nonnegative Matrix Factorization (NMF) in a supervised manner. Using a combinative transfer learning and semi-supervised learning framework, two different Convolutional Neural Networks (CNN) are trained using synthetic data, approximated strongly labeled data, and unlabeled data where one model will produce the audio tags. In contrast, the other will produce the frame-level prediction. The proposed methodology is then evaluated on three different subsets of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 dataset: validation dataset, challenge evaluation dataset, and public YouTube evaluation dataset. Based on the results, our proposed methodology outperforms the baseline system by a minimum of 7% across these three different data subsets. In addition, our proposed method also outperforms the top 3 submissions from the DCASE 2019 challenge task 4 on the validation and public YouTube evaluation datasets. Our system performance is also competitive against the top submission in DCASE 2020 challenge task 4 on the challenge evaluation data. A post-challenge analysis was also performed using the validation dataset, which revealed the causes of the performance difference between our system and the top submission of the DCASE 2020 challenge task 4. The leading causes that we observed are 1) detection threshold tuning method and 2) augmentation techniques used. We observed that our system could perform better than the first place submission by 1.5% by changing our detection threshold tuning method. In addition, the post-challenge analysis also revealed that our system is more robust than the top submission in DCASE 2020 challenge task 4 on long-duration audio clips, where we outperformed them by 37%.

show abstract

Comparative Assessment of Data Augmentation for Semi-Supervised Polyphonic Sound Event Detection

Cited by 6 publications

References 18 publications

Recording and Analyzing Infrasounds to Monitor Human Activities in Buildings

Recording and Analyzing Infrasounds to Monitor Human Activities in Buildings

An Analysis of Sound Event Detection under Acoustic Degradation Using Multi-Resolution Systems

Semi-Supervised NMF-CNN for Sound Event Detection

Contact Info

Product

Resources

About