臺灣博碩士論文加值系統

抹香鯨(Sperm Whale)是世界上最大的齒鯨類哺乳動物，擁有高度發展社交制度的物種，使用各種不同類型的脈衝序列組合出多樣的訊號來進行社交溝通。
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）作特徵分析與分類。聲音來源取自於CIBRA (Centor Interdisciplinare di Bioacusticae Ricerche Ambientali)及TCOML (The Cornel Lab of Ornithology Macaulay Library)的抹香鯨聲音檔，其中除了抹香鯨聲音外，也掺雜了背景雜音。我們利用頻譜相減法將背景雜訊去除之後，建立時頻圖並分析聲紋的差異，選取脈衝序列的時間間隔的最大值、最小值與平均值作為其特徵值，再利用K-means分群法進行聲紋的分類。特徵分析結果發現，抹香鯨的點擊和尾波聲紋雖然都是由脈衝訊號所組成，但是脈衝的型態與時間間隔有顯著的差異。分類結果發現有100%的正確率。

Sperm whale is the world's largest species of odontoceti mammals, has highly developed social system, practices different pulse sequence combinations to perform social communication.
In this thesis, we focus on two voiceprints, Clicks and Codas, of sperm whale to perform their feature analysis and classification. The source audio files are retrieved from CIBRA (Centor Interdisciplinare di Bioacusticae Ricerche Ambientali) and TCOML (The Cornel Lab of Ornithology Macaulay Library), in which background noises are included except for the bottlenose dolphin’s voices. We use spectral subtraction method to eliminate background noise, construct spectrograms of these two voiceprints via time-frequency analysis, extract the maximum, minimum and average values of inter-click intervals (ICIs) as features, and perform classification by k-means clustering method. Feature analysis results show that both Clicks and Codas consist of pulse sequences, but their patterns as well as the averaged values of ICIs are quite different. Clustering analysis shows that 100% of correct classification can be achieved.

摘要 I
Abstract II
目錄 III
圖目錄 IV
表目錄 VI
第一章 緒論 1
1.1前言 1
1.2研究動機與目的 1
1.3論文大綱 2
第二章 相關知識和技術理論基礎 3
2.1抹香鯨聲紋行為的意涵 3
2.1.1點擊 3
2.1.2咯吱 4
2.1.3尾波 5
2.2頻譜刪減法 6
2.3時頻分析 7
2.3.1數位化 8
2.3.2離散傅立葉轉換 8
2.3.3短時距傅立葉轉換 9
2.3.4漢明窗(Hamming Window) 9
2.4 K-means分群法(K-means clustering) 10
第三章 抹香鯨聲紋特徵分析和分群 14
3.1噪音去除 15
3.2時頻分析 18
3.3特徵值提取 21
第四章 結果討論與分析 22
4.1 Clicks分析結果 22
4.2 Codas分析結果 34
4.3 K-means分群法分類結果 43
第五章 結論與未來展望 50
5.1結論 50
5.2未來展望 50
參考文獻 51

[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] V. Drouot and A. Gannier, “New sperm whale vocalizations recorded in the meditterranean sea,” European Research on Cetacean, 1999.

[4] 中華民鯨豚協會網站，http://www,whale.org.tw/。

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

[6] 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.

[7] 洪賢昇， “DSP Lecture 4：Sampling and Reconstruction of Analog Signals,”海洋大學電機工程學系，DSP課程講義。

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

[9] J. A. Hartigan and M. A. Wong, “A K-Means Clustering Algorithm,” Applied Statistics, vol. 28, No. 1, pp. 100-108,1979.

[10] Chung-Chen Chen, http://ccckmit.wikdot.com/ai:kmeans ,pp.16, 2009.

[11] TCOML，http://macaulaylibrary.org/search?&asset_format_id=1000&collection_type_id=1&layout=1&taxon=Sperm&taxon_id=10530453&taxon_rank_id=55&sort=21。

[12] CSI Computerized Scanning and Imaging Facility，
http://csi.whoi.edu/audio/spermwhale-audio-II。

[13] DOSITS，http://www.dosits.org/galleries/audio/marinemammals/toothedwhales/spermwhale/。

[14] 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.