魚類聲音萃取與台灣魚類聲音資料庫之架構

The Extraction of Fish Sounds and the Development of Sound Archive for Fishes in Taiwan

魏瑞昌 ； 劉祐麟

《中華民國音響學刊》 14期 (2010/07) Pp. 85-98

https://doi.org/10.30049/JASRC.201007.0006

摘要

台灣魚類聲音資料庫的建立，可以有系統儲存聲音樣本的詳細資訊，除此之外還可提供一個資訊交流平台，增加研究人員在生物行為、物種辨認以及定位追蹤等研究的便利性。在進行資料上傳之前，資料庫會計算聲音樣本的訊雜比作為品質分析結果，提供使用者選擇聲音樣本的一項參考。由於資料來源有實際海域錄音與水族箱錄音兩大類，為了正確框選出魚類聲音訊號，本文用兩種端點偵測法進行萃取，當聲音樣本是實際海域錄音時，採用時域端點法；當聲音樣本為水族箱錄音時，採用頻率端點法。最後配合偵測結果計算魚類訊號與背景值的平均功率，得到聲音樣本的訊雜比。資料庫採用三層式架構進行資料庫建立，為了降低資料的儲存容量同時保持資料完整性，以關聯模式作為資料儲存的格式。本資料庫除了提供資料上傳的平台外，還提供生物名稱、錄音地點、錄音時間三種搜尋方式，希望增加使用者使用資料庫的便利性與效率。

關鍵字

魚類聲音 ； 資料庫 ； 時域端點法 ； 頻率端點法

並列摘要

The goal of development of sound archive for marine fishes in Taiwan is not only to preserve data, but also wants to provide a platform of data sharing to increase the efficiency for the study of fish behavior, automatic recognition, localization, and tracking. In order to provide the sound quality in terms of signal-to-noise ratio to users, the fish sound recording will be analyzed before uploading. Because most available data were recorded either in the field or in fish tank, the fish sounds were extracted by using two different automatic detection methods. If fish sound recordings were from the field, the Time Endpoint Detection was applied. If the recording was made in the fish tank, the Frequency Endpoint Detection was applied. From two different automatic detection methods, the sound quality was presented in the signal-to-noise ratio, which was the averaged power of signal divided by averaged power of the background noise. The archive was a 3-Tier system and in order to reduce the storage size and maintain the integrity of data, the Relational Model was applied. To improve the users' efficiency the database provides not only data uploading, but also data searching according to creature name, recording area, and recording time.

並列關鍵字

fish sounds ； database ； time endpoint detection ； frequency endpoint detection