Evidence for acoustic discrimination in lemurs: A playback study on wild indris Indri indri

Abstract

Indris Indri indri are group-living lemurs that occupy stable territories over several years and perform remarkable long-distance vocal displays. Vocal exchanges between long-term territory neighbors may contribute to assessing reciprocal resource-holding potentials, thus adaptively reducing the costs of territorial defense by limiting aggressive escalation. Previous work showed that indris' songs show distinctive acoustic features at individual and group level. However, the possibility that indris use such cues for individual or group-level recognition has never been investigated experimentally. We conducted a playback experiment to test whether indris discriminate between familiar and nonfamiliar songs. Our rationale lies in the hypothesis of the dear enemy phenomenon, which predicts that territorial animals will show reduced aggression levels toward familiar neighbors compared with novel rivals. We played back stimulus recordings to wild indris from their territory boundaries and examined their responses in terms of vocal and behavioral indicators of willingness to engage in a fight. In line with our predictions, focal animals responded more rapidly and approached more often the speaker in response to playback stimuli of nonfamiliar individuals than to stimuli of neighboring groups. These results indicate that indris can discriminate between different classes of intruders based on distinctive acoustic features of their song choruses. We suggest that increased aggression directed toward unfamiliar intruders may be explained by higher threat levels associated with dispersal and group formation dynamics. We further discuss the relevance of these findings in a strepsirrhine primate model for comparative studies of vocal communication and sociality.

Keywords: acoustic communication; dear-enemy effect; neighbor–stranger discrimination; primate communication; song; territoriality.

Figure 1.

Duration of reply songs (in seconds) to playback stimuli as a function of the number of singing individuals. Depicted is the fitted model (black line) with the 95% CIs (gray shading).

Figure 2.

(A) Latency (in seconds) of subject groups to respond to playback stimuli plotted against playback type. Horizontal lines indicate the fitted model with the respective 95% CIs. (B) Proportions of playback stimuli (±SE) approached by the subject groups to the source of the stimulus. Proportions are shown separately for sex and playback type.