請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98582完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張智星 | zh_TW |
| dc.contributor.advisor | Jyh-Shing Roger Jang | en |
| dc.contributor.author | 姜毅希 | zh_TW |
| dc.contributor.author | Yi-Hsi Chiang | en |
| dc.date.accessioned | 2025-08-18T00:57:54Z | - |
| dc.date.available | 2025-08-18 | - |
| dc.date.copyright | 2025-08-15 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-08-07 | - |
| dc.identifier.citation | [1] M. I. Ansari and T. Hasan. SpectNet : End-to-End audio signal classification using learnable spectrograms. arXiv (Cornell University), 1 2022.
[2] D. Barchiesi, D. Giannoulis, D. Stowell, and M. D. Plumbley. Acoustic Scene Classification: Classifying environments from the sounds they produce, 5 2015. [3] U. Cappellazzo, D. Falavigna, A. Brutti, and M. Ravanelli. Parameter-Efficient Transfer learning of Audio Spectrogram transformers. arXiv (Cornell University), 1 2023. [4] Z. Chen, H. Cui, J. Xiang, K. Qiu, L. Huang, S. Zheng, S. Chen, Q. Xuan, and X. Yang. SIGNET: a novel deep learning framework for radio signal classification. arXiv (Cornell University), 1 2020. [5] K. Choi, G. Fazekas, K. Cho, and M. Sandler. A comparison of audio signal preprocessing methods for deep neural networks on music tagging. arXiv (Cornell University), 1 2017. [6] S.-Y. Chou, K.-H. Cheng, J.-S. R. Jang, and Y.-H. Yang. Learning to match transient sound events using attentional similarity for few-shot sound recognition, 5 2019. [7] M.-I. Georgescu, E. Fonseca, R. T. Ionescu, M. Lucic, C. Schmid, and A. Arnab. Audiovisual Masked autoencoders, 12 2022. [8] Y. Gong, Y.-A. Chung, and J. Glass. AST: Audio Spectrogram Transformer. arXiv (Cornell University), 1 2021. [9] P. Grant and M. Z. Islam. Signal Classification using Smooth Coefficients of Multiple wavelets. arXiv (Cornell University), 1 2021. [10] S. Hershey, S. Chaudhuri, D. P. W. Ellis, J. F. Gemmeke, A. Jansen, R. C. Moore, M. Plakal, D. Platt, R. A. Saurous, B. Seybold, M. Slaney, R. J. Weiss, and K. Wilson. CNN Architectures for Large-Scale Audio Classification. arXiv (Cornell University), 1 2016. [11] M. Huzaifah. Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks. arXiv (Cornell University), 1 2017. [12] S. Jeon, C.-F. Yeh, H. Inan, W.-N. Hsu, R. Rungta, Y. Mehdad, and D. Bikel. Attention or convolution: transformer encoders in audio language models for inference efficiency. arXiv (Cornell University), 1 2023. [13] Q. Kong, Y. Cao, T. Iqbal, Y. Wang, W. Wang, and M. D. Plumbley. PANNS: Large-Scale pretrained audio neural networks for audio pattern recognition, 12 2019. [14] J. Li, W. Dai, F. Metze, S. Qu, and S. Das. A Comparison of deep learning methods for environmental sound. arXiv (Cornell University), 1 2017. [15] Q. Li, H. Peng, J. Li, C. Xia, R. Yang, L. Sun, P. S. Yu, and L. He. A survey on text classification: From shallow to Deep learning. arXiv (Cornell University), 1 2020. [16] X. Liu, H. Lu, J. Yuan, and X. Li. CAT: Causal Audio Transformer for Audio Classification. arXiv (Cornell University), 1 2023. [17] D. Niizumi, D. Takeuchi, M. Yasuda, B. T. Nguyen, Y. Ohishi, and N. Harada. M2D2: Exploring General-Purpose Audio-Language Representations Beyond CLAP, 3 2025. [18] R. Palaniappan, K. Sundaraj, and S. Sundaraj. A comparative study of the svm and k-nn machine learning algorithms for the diagnosis of respiratory pathologies using pulmonary acoustic signals. BMC bioinformatics, 15:223, 06 2014. [19] K. J. Piczak. ESC: Dataset for Environmental Sound Classification. In Proceedings of the 23rd Annual ACM Conference on Multimedia, pages 1015–1018. ACM Press. [20] K. J. Piczak. Environmental sound classification with convolutional neural networks, 9 2015. [21] J. Pons, J. Serrà, and X. Serra. Training neural audio classifiers with few data, 10 2018. [22] H. Purwins, B. Li, T. Virtanen, J. Schluter, S.-Y. Chang, and T. Sainath. Deep learning for audio signal processing. IEEE Journal of Selected Topics in Signal Processing, 13(2):206–219, 4 2019. [23] V. Rathikarani, P. Dhanalakshmi, and P. S. Classification of musical instruments using svm and knn. International Journal of Innovative Technology and Exploring Engineering, 9:2278–3075, 05 2020. [24] M. Schmitt and B. Schuller. End-to-end Audio Classification with Small Datasets – Making It Work, 9 2019. [25] Y. Shi, K. Davaslioglu, Y. E. Sagduyu, W. C. Headley, M. Fowler, and G. Green. Deep learning for RF signal classification in unknown and dynamic spectrum environments. arXiv (Cornell University), 1 2019. [26] K. Simonyan and A. Zisserman. Very deep convolutional networks for Large-Scale image recognition, 9 2014. [27] J. Snell, K. Swersky, and R. S. Zemel. Prototypical networks for few-shot learning, 3 2017. [28] G. Tzanetakis and P. Cook. Musical genre classification of audio signals, 7 2002. [29] G. Wang, C. Li, F. Tang, Y. Wang, S. Wu, H. Zhi, F. Zhang, M. Wang, and J. Zhang. A fully-automatic semi-supervised deep learning model for difficult airway assessment. Heliyon, 9(5):e15629, 4 2023. [30] Y. Wang, N. J. Bryan, J. Salamon, M. Cartwright, and J. P. Bello. Who calls the shots? Rethinking Few-Shot Learning for Audio. arXiv (Cornell University), 1 2021. [31] P. Wolters, C. Careaga, B. Hutchinson, and L. Phillips. A study of Few-Shot Audio Classification, 12 2020. [32] B. Zhu, K. Xu, D. Wang, L. Zhang, B. Li, and Y. Peng. Environmental Sound Classification Based on Multi-temporal Resolution Convolutional Neural Network Combining with Multi-level Features. arXiv (Cornell University), 1 2018. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98582 | - |
| dc.description.abstract | 音訊分類技術在各種應用領域中皆具有重要性，尤其在異常事件偵測方面更扮演關鍵角色。本研究與旭儀企業股份有限公司合作，針對自來水管漏水聲之偵測問題進行探討。我們提出一種結合原型網路（prototypical network）與 VGG11 圖像分類模型的架構，並進一步引入本研究所設計的改良方案，以提升分類效能。為驗證所提方法之準確性與穩定性，我們採用公開音訊分類資料集 ESC-50 進行實驗。實驗結果顯示，本方法在處理漏水聲音訊分類任務上具備良好之辨識能力，顯示其應用潛力。 | zh_TW |
| dc.description.abstract | Audio classification plays a critical role in various application domains, particularly in the detection of abnormal events. In this study, we collaborated with ASAHI SUNRISE CO., LTD. to investigate the problem of detecting water leakage sounds in water pipelines. We propose a method that integrates the prototypical network framework with the VGG11 image classification model, along with enhancements specifically designed for this task. To evaluate the accuracy and robustness of the proposed approach, we conducted experiments using the publicly available ESC-50 audio classification dataset. The experimental results demonstrate that our method achieves promising performance in detecting water leakage sounds, indicating its potential for practical applications. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-08-18T00:57:54Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-08-18T00:57:54Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 i
摘要 iii Abstract v 目次 vii 圖次 xi 表次 xiii 第一章 緒論 1 1.1 研究背景 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 研究簡介與動機 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.3 研究貢獻 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.4 章節概述 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 第二章 文獻探討 5 2.1 基於傳統訊號處理與機器學習的音訊分類方法 . . . . . . . . . . . . 5 2.2 基於深度學習的音訊分類方法 . . . . . . . . . . . . . . . . . . . . . 6 第三章 資料集介紹 7 3.1 CY-dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 3.2 ESC-50 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 3.3 資料集匯總 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 第四章 研究方法 9 4.1 資料前處理 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 4.1.1 特徵提取 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 4.1.2 資料集分割 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 4.2 預訓練模型 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 4.3 原型網路 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 4.3.1 訓練機制 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 4.3.2 預測機制 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.4 原型網路的改良 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.4.1 損失函數 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.4.2 原型計算 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.4.2.1 平均值法 . . . . . . . . . . . . . . . . . . . . . . . . 17 4.4.2.2 K-means 分群法 . . . . . . . . . . . . . . . . . . . . . 18 4.4.2.3 Attention Layer . . . . . . . . . . . . . . . . . . . . . 19 4.5 模型評估方法 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 第五章 實驗設計和結果討論 23 5.1 實驗流程與設定 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 5.1.1 實驗環境 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 5.1.2 實驗參數設定 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 5.1.2.1 XGBoost 實驗設定 . . . . . . . . . . . . . . . . . . . 24 5.1.2.2 SVM 實驗設定 . . . . . . . . . . . . . . . . . . . . . 24 5.1.2.3 VGG11 實驗設定 . . . . . . . . . . . . . . . . . . . . 25 5.1.2.4 原型網路實驗設定 . . . . . . . . . . . . . . . . . . . 25 5.1.3 實驗路線圖 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 5.1.4 評量指標 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 5.1.5 基準實驗流程 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 5.1.6 基礎原型網路架構實驗流程 . . . . . . . . . . . . . . . . . . . . 28 5.1.7 損失函數改良實驗流程 . . . . . . . . . . . . . . . . . . . . . . . 29 5.1.8 原型計算改良實驗流程 . . . . . . . . . . . . . . . . . . . . . . . 29 5.2 基準實驗 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 5.3 基礎原型網路架構實驗 . . . . . . . . . . . . . . . . . . . . . . . . . 31 5.4 損失函數改良實驗 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 5.4.1 VGG11 + 改良損失函數之原型網路 . . . . . . . . . . . . . . . . 33 5.4.2 損失函數自定義係數的調整 . . . . . . . . . . . . . . . . . . . . 36 5.5 原型計算改良實驗 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 5.5.1 平均值法 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 5.5.2 K-means 分群法 . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 5.5.3 Attention Layer . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46 5.6 實驗結果與探討 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 第六章 結論與未來展望 51 6.1 結論 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 6.2 未來展望 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52 參考文獻 55 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 音訊分類 | zh_TW |
| dc.subject | 少量資料 | zh_TW |
| dc.subject | 特徵提取 | zh_TW |
| dc.subject | 原型網路 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | Machine learning | en |
| dc.subject | Prototypical network | en |
| dc.subject | Feature extraction | en |
| dc.subject | Audio classification | en |
| dc.subject | Few data | en |
| dc.title | 以少量資料進行自來水管漏水聲偵測 | zh_TW |
| dc.title | Detection of Water Pipe Leakage Sounds with Limited Data | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 王新民;陳冠宇 | zh_TW |
| dc.contributor.oralexamcommittee | Hsin-Min Wang;Kuan-Yu Chen | en |
| dc.subject.keyword | 少量資料,音訊分類,機器學習,原型網路,特徵提取, | zh_TW |
| dc.subject.keyword | Few data,Audio classification,Machine learning,Prototypical network,Feature extraction, | en |
| dc.relation.page | 58 | - |
| dc.identifier.doi | 10.6342/NTU202502217 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2025-08-11 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| dc.date.embargo-lift | N/A | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf 未授權公開取用 | 11.39 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。