Automatic acoustic detection of birds through deep learning: the first Bird Audio Detection challenge

Stowell, Dan; Stylianou, Yannis; Wood, M. H.; Pamuła, Hanna; Glotin, Hervé

doi:10.48550/arxiv.1807.05812

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[15]. Deep Learning adalah cara untuk mengotomatisasi pekerjaan untuk memprediksi dan mengklasifikasikan data menggunakan jaringan saraf tiruan (artificial neural networks) dengan banyak lapisan (atau "deep") untuk memodelkan abstraksi data yang kompleks [16]. Proses pemasukan data, pengolahan dan penyajiannya akan dilakukan secara otomatis oleh mesin.…”

Section: Pendahuluanunclassified

Pemodelan Wilayah Titik Api Kebakaran Hutan Menggunakan Deep Learning

Dwiasnati,

Devianto,

Arif

et al. 2024

FIFO

View full text Add to dashboard Cite

Indonesia merupakan negara tropis yang mengalami kebakaran hutan setiap tahunnya. Kebakaran hutan terjadi disebabkan oleh durasi musim panas yang terlalu lama dari waktu semestinya. Hutan merupakan tempat tinggal berbagai jenis satwa dan fauna yang memiliki banyak kekayaan hayati yang dapat membuat mereka bertahan hidup. Sering terjadinya kebakaran hutan menjadi isu lingkungan yang dianggap krusial dan mendapatkan perhatian baik dari tingkat lokal maupun internasional. Penelitian yang dilakukan ini menyajikan kajian klasifikasi wilayah titik api kebakaran hutan menggunakan salah satu algoritma Deep Learning (DL) yaitu metode Convolutional Neural Network (CNN), hal ini sangat dibutuhkan untuk pendahuluan mengenai peringatan dini kebakaran hutan yang ada di daerah tersebut. Wilayah titik api kebakaran hutan yang digunakan dalam penelitian ini dikumpulkan dari daerah Nusa Tenggara Timur (NTT), terutama pulau-pulau seperti Sumba dan Timor. Metode CNN melibatkan dua langkah utama. Langkah pertama adalah pengklasifikasian gambar melalui proses feedforward. Langkah kedua adalah fase pembelajaran menggunakan teknik backpropagation. Model CNN yang digunakan dalam proses pelatihan dataset menguji citra dengan beberapa pengoptimal dan diperoleh hasil akurasi yang tinggi. Kemiripan area yang terbakar dengan fitur terang lainnya mengurangi kepastian deteksi kebakaran hutan. Hasil penelitian menunjukkan bahwa Model CNN yang digunakan Untuk deteksi dan segmentasi area terbakar menggunakan algoritma terpilih, kinerja terbaik dengan pembelajaran mendalam yang dilaporkan dalam literatur adalah 89%.Teknik yang diusulkan dilatih menggunakan wilayah varian (kumpulan data) dan mengevaluasi presisi berdasarkan ambang recall, dengan akurasi keseluruhan 89%.

show abstract

Section: Pendahuluanunclassified

Pemodelan Wilayah Titik Api Kebakaran Hutan Menggunakan Deep Learning

Dwiasnati,

Devianto,

Arif

et al. 2024

FIFO

View full text Add to dashboard Cite

show abstract

“…This is especially true when considering the utilization of audio data to perform various audio recognition tasks, which have recently attracted increasing interest from researchers. As a result, numerous audio recognition systems have been developed, such as for wildlife monitoring [28,36] and surveillance [5]. In addition to monitoring applications, highly accurate acoustic models are utilized for keyword spotting for virtual assistants [23], anomaly detection for machine sounds [18], and in the development of health risk diagnosis systems, such as cardiac arrest detection [4].…”

Section: Introductionmentioning

confidence: 99%

Federated Self-training for Semi-supervised Audio Recognition

Tsouvalas

Saeed

Özçelebi

2022

ACM Trans. Embed. Comput. Syst.

View full text Add to dashboard Cite

Federated Learning is a distributed machine learning paradigm dealing with decentralized and personal datasets. Since data reside on devices like smartphones and virtual assistants, labeling is entrusted to the clients or labels are extracted in an automated way. Specifically, in the case of audio data, acquiring semantic annotations can be prohibitively expensive and time-consuming. As a result, an abundance of audio data remains unlabeled and unexploited on users’ devices. Most existing federated learning approaches focus on supervised learning without harnessing the unlabeled data. In this work, we study the problem of semi-supervised learning of audio models via self-training in conjunction with federated learning. We propose FedSTAR to exploit large-scale on-device unlabeled data to improve the generalization of audio recognition models. We further demonstrate that self-supervised pre-trained models can accelerate the training of on-device models, significantly improving convergence within fewer training rounds. We conduct experiments on diverse public audio classification datasets and investigate the performance of our models under varying percentages of labeled and unlabeled data. Notably, we show that with as little as 3% labeled data available, FedSTAR on average can improve the recognition rate by 13.28% compared to the fully-supervised federated model.

show abstract

“…This is especially true when considering the utilization of audio data to perform various audio recognition tasks, which have recently attracted increasing interest from researchers. As a result, numerous audio recognition systems have been developed, such as for wildlife monitoring [27,35] and surveillance [5]. In addition to monitoring applications, highly accurate acoustic models are utilized for keyword spotting for virtual assistants [23], anomaly detection for machine sounds [18], and in the development of health risk diagnosis systems, such as cardiac arrest detection [4].…”

Section: Introductionmentioning

confidence: 99%

Federated Self-Training for Semi-Supervised Audio Recognition

Tsouvalas¹,

Saeed²,

Özçelebi³

2021

Preprint

View full text Add to dashboard Cite

Federated Learning is a distributed machine learning paradigm dealing with decentralized and personal datasets. Since data reside on devices like smartphones and virtual assistants, labeling is entrusted to the clients or labels are extracted in an automated way. Specifically, in the case of audio data, acquiring semantic annotations can be prohibitively expensive and time-consuming. As a result, an abundance of audio data remains unlabeled and unexploited on users' devices. Most existing federated learning approaches focus on supervised learning without harnessing the unlabeled data. In this work, we study the problem of semi-supervised learning of audio models via self-training in conjunction with federated learning. We propose FedSTAR 1 to exploit large-scale on-device unlabeled data to improve the generalization of audio recognition models. We further demonstrate that self-supervised pre-trained models can accelerate the training of on-device models, significantly improving convergence to within fewer training rounds. We conduct experiments on diverse public audio classification datasets and investigate the performance of our models under varying percentages of labeled and unlabeled data. Notably, we show that with as little as 3% labeled data available, FedSTAR on average can improve the recognition rate by 13.28% compared to the fully-supervised federated model. CCS Concepts: • Computing methodologies → Semi-supervised learning settings; Neural networks; • Human-centered computing → Ubiquitous and mobile computing.

show abstract

Automatic acoustic detection of birds through deep learning: the first Bird Audio Detection challenge

Cited by 4 publications

References 0 publications

Pemodelan Wilayah Titik Api Kebakaran Hutan Menggunakan Deep Learning

Pemodelan Wilayah Titik Api Kebakaran Hutan Menggunakan Deep Learning

Federated Self-training for Semi-supervised Audio Recognition

Federated Self-Training for Semi-Supervised Audio Recognition

Contact Info

Product

Resources

About