Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2509.17800

Convolutional Neural Network Optimization for Beehive Classification Using Bioacoustic Signals

Harshit·Rahul Jana·Ritesh Kumar
View original source ↗Read source document ↗Export metadata ↓

Abstract

The behavior of honeybees is an important ecological phenomenon not only in terms of honey and beeswax production but also due to the proliferation of flora and fauna around it. The best way to study this significant phenomenon is by non-invasive monitoring of beehives using the sounds produced by various body movements that give out audio signals which can be exploited for various predictions related to the objectives mentioned above. This study investigates the application of Convolutional Neural Networks to classify and monitor different hive states with the help of joint time and frequency image representations such as Spectrogram, Mel-Spectrogram, Smoothed-Spectrogram, and Cochleagram. Our findings indicate that the Cochleagram outperformed all the other representations, achieving an accuracy of 98.31% on unseen data. Furthermore, we employed various strategies including pruning, quantization, and knowledge distillation to optimize the network and prevent any potential issues with model size. With these optimizations, the network size was lowered by 91.8% and the inference time was accelerated by 66%, increasing its suitability for real-time applications. Thus our study emphasizes the significance of using optimization approaches to minimize model size, avoid deployment problems, and expedite inference for real-time application as well as the selection of an appropriate time-frequency representation for optimal performance.

Explore related subjects

cs.SDcs.OH

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Harshit, Rahul Jana, Ritesh Kumar. 2025-09-22. Convolutional Neural Network Optimization for Beehive Classification Using Bioacoustic Signals. https://arxiv.org/abs/2509.17800

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Xiaomi-CocktailASR-1 Technical Report

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

cs.SD↗
arXiv2026

EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation

Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.

cs.SD↗