San Diego State University, Department of Computer Science, 5500 Campanile Drive, San Diego, California 92182-7720, USA.
J Acoust Soc Am. 2011 Oct;130(4):2212-23. doi: 10.1121/1.3624821.
Many odontocetes produce frequency modulated tonal calls known as whistles. The ability to automatically determine time × frequency tracks corresponding to these vocalizations has numerous applications including species description, identification, and density estimation. This work develops and compares two algorithms on a common corpus of nearly one hour of data collected in the Southern California Bight and at Palmyra Atoll. The corpus contains over 3000 whistles from bottlenose dolphins, long- and short-beaked common dolphins, spinner dolphins, and melon-headed whales that have been annotated by a human, and released to the Moby Sound archive. Both algorithms use a common signal processing front end to determine time × frequency peaks from a spectrogram. In the first method, a particle filter performs Bayesian filtering, estimating the contour from the noisy spectral peaks. The second method uses an adaptive polynomial prediction to connect peaks into a graph, merging graphs when they cross. Whistle contours are extracted from graphs using information from both sides of crossings. The particle filter was able to retrieve 71.5% (recall) of the human annotated tonals with 60.8% of the detections being valid (precision). The graph algorithm's recall rate was 80.0% with a precision of 76.9%.
许多齿鲸类动物会发出调频的音调叫声，称为口哨声。自动确定与这些发声相对应的时间×频率轨迹的能力具有许多应用，包括物种描述、识别和密度估计。这项工作在南加州湾和帕尔米拉环礁收集的近一小时共同语料库上开发和比较了两种算法。该语料库包含了超过 3000 个来自宽吻海豚、长吻海豚、飞旋海豚和瓜头鲸的口哨声，这些口哨声已经由人类进行了注释，并发布到了 Moby Sound 档案中。两种算法都使用一个共同的信号处理前端从声谱图中确定时间×频率峰值。在第一种方法中，粒子滤波器执行贝叶斯滤波，从噪声频谱峰值估计轮廓。第二种方法使用自适应多项式预测将峰值连接成一个图，当它们交叉时合并图。使用交叉点两侧的信息从图中提取口哨声轮廓。粒子滤波器能够以 60.8%的检测准确率（精度）恢复 71.5%（召回率）的人类标注的音调。图形算法的召回率为 80.0%，准确率为 76.9%。
