The study of cetacean vocalizations is usually based on spectrogram analysis. The feature extraction is obtained from 2D methods like the edge detection algorithm. Difficulties appear when signal-to-noise ratios are weak or when more than one vocalization is simultaneously emitted. This is the case for acoustic observations in a natural environment and especially for the killer whales which swim in groups. To resolve this problem, we propose the use of the Hilbert-Huang transform. First, we illustrate how few modes (5) are satisfactory for the analysis of these calls. Then, we detail our approach which consists of combining the modes for extracting the time-varying frequencies of the vocalizations. This combination takes advantage of one of the empirical mode decomposition properties which is that the successive IMFs represent the original data broken down into frequency components from highest to lowest frequency. To evaluate the performance, our method is first applied on the simulated chirp signals. This approach allows us to link one chirp to one mode. Then we apply it on real signals emitted by killer whales. The results confirm that this method is a favorable alternative for the automatic extraction of killer whale vocalizations.