Automated extraction of odontocete whistle contours

作者：Roch Marie A^*; Brandes T Scott; Patel Bhavesh; Barkley Yvonne; Baumann Pickering Simone; Soldevilla Melissa S

来源：Journal of the Acoustical Society of America, 2011, 130(4): 2212-2223.

DOI：10.1121/1.3624821

• Automated extraction
• Bayesian filtering
• Bottlenose dolphins
• Common signal processing
• Density estimation
• Frequency modulated
• Front end
• Graph algorithms
• Melon-headed whale
• Odontocetes
• Particle filter
• Recall rate
• Sound archives
• Southern California Bight
• Spectral peak
• Spectrograms
• Time frequency

Many odontocetes produce frequency modulated tonal calls known as whistles. The ability to automatically determine time x 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 x 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%.

• 出版日期2011-10