Automatic detection and taxonomic identification of dolphin vocalisations using convolutional neural networks for passive acoustic monitoring

With the rapid popularization of Internet big data worldwide, people are able to transmit, download, and listen to huge amounts of music, which directly contributes to the demand for music information retrieval. In this paper, a music information retrieval system is constructed based on extracting music features. Both time and frequency domains characterize the music, and the transformation relationship between time domain, frequency domain, cepstrum domain, and power spectrum is proposed to extract music features. Further, the convolutional deep confidence network algorithm is applied to music information retrieval, an unsupervised greedy layer-by-layer algorithm carries out pre-training, and the network parameters are adjusted to improve the retrieval and recognition ability of the model. Functional validation of the system in this paper. In the music feature extraction experiments in this paper, the system’s accuracy for extracting feature points from different songs is more than 80%. In the music information retrieval experiments in nine different styles of music in the style of music in this paper, the average judgment of the system correct rate of 92.59%, in different proportions of the number of tracks in the retrieval success rate, is higher than 88%. In music analysis fields such as music recommendation and music soundtrack design, the music information retrieval system constructed in this paper plays a significant role.

show abstract

Early Prediction of Harmful Environmental Changes Based on Bioacoustics Analysis

Jayanthi,

Chitradevi,

Muthaiyah

2024

Advances in Environmental Engineering and Green Technologies

View full text Add to dashboard Cite

Environmental conditions of ocean are crucial for predicting harmful events, which gives an impact on marine ecosystems and human well-being. Various threats, such as ocean acidification, harmful algal blooms, and coral bleaching, need early monitoring of variables, including temperature, acidity, pollution levels, and biodiversity, to mitigate the adverse effects. This proactive approach enables conservation efforts that safeguard marine life, fisheries, and coastal communities while promoting sustainable ocean stewardship. Deep learning techniques play a pivotal role in this endeavour by processing underwater acoustic recordings. It gives accurate results to identify marine species, detect changes in their behavior, and predict environmental conditions based on sound patterns. The proposed work suggests that, combination of Long Short Term Memory(LSTM) and Graphical Neural Network(GNN) which is used to predict the harmful changes over the ocean. LSTM and GNN architectures establish an indirect relationship, shedding light on emerging trends and potential threats.

show abstract

Automatic detection and taxonomic identification of dolphin vocalisations using convolutional neural networks for passive acoustic monitoring

Cited by 3 publications

References 55 publications

Trajectory-based fish event classification through pre-training with diffusion models

Trajectory-based fish event classification through pre-training with diffusion models

The Contribution of Music Information Retrieval System Optimization to Music Analysis in the Context of Big Data

Early Prediction of Harmful Environmental Changes Based on Bioacoustics Analysis

Contact Info

Product

Resources

About