Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2011.14336

An Features Extraction and Recognition Method for Underwater Acoustic Target Based on ATCNN

Gang Hu·Kejun Wang·Liangliang Liu
View original source ↗Read source document ↗Export metadata ↓

Abstract

Facing the complex marine environment, it is extremely challenging to conduct underwater acoustic target recognition (UATR) using ship-radiated noise. Inspired by neural mechanism of auditory perception, this paper provides a new deep neural network trained by original underwater acoustic signals with depthwise separable convolution (DWS) and time-dilated convolution neural network, named auditory perception inspired time-dilated convolution neural network (ATCNN), and then implements detection and classification for underwater acoustic signals. The proposed ATCNN model consists of learnable features extractor and integration layer inspired by auditory perception, and time-dilated convolution inspired by language model. This paper decomposes original time-domain ship-radiated noise signals into different frequency components with depthwise separable convolution filter, and then extracts signal features based on auditory perception. The deep features are integrated on integration layer. The time-dilated convolution is used for long-term contextual modeling. As a result, like language model, intra-class and inter-class information can be fully used for UATR. For UATR task, the classification accuracy reaches 90.9%, which is the highest in contrast experiment. Experimental results show that ATCNN has great potential to improve the performance of UATR classification.

Explore related subjects

cs.SDeess.AS

Keep this discovery

BibTeXRIS

Gang Hu, Kejun Wang, Liangliang Liu. 2020-11-29. An Features Extraction and Recognition Method for Underwater Acoustic Target Based on ATCNN. https://arxiv.org/abs/2011.14336

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↗