臺灣博碩士論文加值系統

抹香鯨擁有高度的智慧，是世界上最大的齒鯨類哺乳動物，會藉由發出不同的聲音來進行互相溝通以及社交行為。藉由收集鯨豚的聲音資料，進行特徵分析與分類，可以有助於了解抹香鯨的生物行為模態。
本論文針對抹香鯨所發出的兩種訊號類型，點擊(Clicks）和尾波(Codas）的聲紋特徵資料，利用最大事後概度分類理論來設計最佳分類器，進行抹香鯨的行為模態的分類研究。聲紋特徵資料取自於海洋大學電機工程學系的統計訊號處理實驗室經過多年研究建立的聲紋特徵資料庫。
所設計的分類器，對於加入高斯白雜訊後的聲紋特徵，在不同訊雜比的情況下，進行分類的準確度分析。模擬結果顯示，在訊雜比到達20 dB後，分類的準確度達到100%。





關鍵字: 抹香鯨、聲紋特徵、最大事後概度、最佳分類器

Sperm whale possesses high intelligence and is the world's largest toothed cetacean mammal. It can communicate and establish social activities through different voices. By collecting sperm whales' sound data as well as performing feature analysis and classification, human beings can learn to understand the ecological behavior of sperm whales.
In this thesis, we design an optimum classifier based on the maximum a posteriori probability (MAP) theory to classify the two types of sounds, Clicks and Codas, generated by sperm whales. We adopt these feature data for our research, which were constructed as a database through several years’ efforts and stored in the statistical signal processing laboratory, electrical engineering department of the national ocean university.
Our proposed MAP classifier is used to analyze the classification accuracy of the sound characteristics after adding Gaussian white noise with different signal- to-noise ratios. The simulation results show that the classification accuracy can reach 100% for the signal-to-noise ratio being above a threshold of 20 dB..





Keywords: Sperm Whale, Acoustic Feature, maximum a posteriori probability (MAP)、Optimum Classifier

摘要 I
Abstract II
目次 1
圖目次 2
表目次 3
第一章 緒論 4
1.1前言 4
1.2研究動機與目的 4
1.3論文大綱 4
第二章 抹香鯨的聲紋特徵分析 6
2.1抹香鯨聲紋行為涵義 6
2.1.1點擊 6
2.1.2咯吱 7
2.1.3尾波 8
2.2頻譜刪減法 8
2.3時頻分析 9
2.3.1短時距傅立葉轉換 9
2.3.2漢明窗(Hamming Window) 10
2.4抹香鯨聲紋特徵分析 10
2.4.1 Clicks聲紋分析結果 11
2.4.2 Codas聲紋分析結果 13
第三章 最佳分類器設計 15
3.1 最大事後概度分類理論 15
3.2 MAP分類器的設計 16
第四章 分類結果討論與分析 19
4.1抹香鯨聲紋特徵資料庫 19
4.2分類結果模擬 22
第五章 結論與未來展望 30
5.1結論 30
5.2未來展望 30
參考文獻 31

[1] Linda Weilgart and Hal Whitehead, “Coda communication by sperm whales (Physter macrocephalus) off the Galapagos Island,” Canadian Journal of Zoology,71(4):744-752,1993.

[2] Mike van der Schaar, “An acoustic biometric for sperm whales,” UNIVERSITAT POLIT’ECNICA DE CATALUNYA, 2009.

[3] CIERA，http://www-3.unipv.it/cibra/edu_spermwhale_uk.html

[4]蘇睿頎，K-means分群法在抹香鯨聲紋分類之應用，國立臺灣海洋大學電機工程學系研究所碩士論文，2016年。

[5] Louis L. Scharf , “Statistical Signal Processing: Detection, Estimation, and Time Series Analysis”, Prentice Hall, 1 July. 1991.

[6] Maurício Cantor, Lauren G. Shoemaker, Reniel B. Cabral, César O. Flores,
Melinda Varga & Hal Whitehead ,“Multilevel animal societies can emerge from
cultural transmission” Nature Communications volume6, 08 September 2015.

[7] Jane J. Lee，抹香鯨的語言暗示著文化的存在，National Geographic，
https://www.natgeomedia.com/news/ngnews/1988

[8] Steve F. Boll, “Suppression of acoustic noise in speech using spectral subtraction,” IEEE TRANSACTIONS ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL. ASSP-27, NO. 2, APRIL 1979.

[9] A. V. Oppenheim, R. W. Schafer, Discrtet-Time Signal Processing, Prentice Hall, Inc., 1989.

[10]王信文，抹香鯨聲音時頻特徵分析，國立臺灣海洋大學電機工程學系研究
所碩士論文，2015年。

[11] T.J. Terrell and Lik-Kwan Shark, Digital Signal Processing – A Student Guide,
Macmillan Press LTD.,1996.