Clinical and experimental evidence accumulated over the past 150 years has firmly established that the left hemisphere of the human brain is fundamentally involved in the perception and production of linguistic information [1], [2]. Left hemisphere dominance in linguistic functions is not restricted to specific modalities of communication and, to some extent, is modulated by the handedness of the individual [3]–[6]. Although historically hemispheric specialization has been considered a unique hallmark of human evolution, more recent studies in a host of vertebrates have provided evidence of population-level behavioral and brain asymmetries, suggesting that language is not a necessary condition for the expression of hemispheric specialization [7]–[9]. Notwithstanding, there remains intense scientific debate over whether animals, and particularly nonhuman primates, show hemispheric specialization in the perception and production of species-typical communicative signals and how this might relate to the evolution of language in humans [1], [8], [10]–[14].

With respect to perception of species-typical communicative signals, behavioral and neurological research has yielded somewhat inconsistent findings [15], [16]. For example, a number of investigators have examined behavioral responses or orienting asymmetries in response to species-typical sounds in rats, birds, sea lions, and nonhuman primates including vervet monkeys, rhesus macaques, Japanese macaques, barbary macaques and bonobos. Left hemisphere asymmetries have been reported in many species [17]–[24] while right hemisphere asymmetries have been reported in vervet monkeys [25]. In barbary macaques, no hemispheric asymmetry in response to species-typical calls was found [26]. Ablation studies and, more recently, functional imaging studies have similarly revealed mixed results [15], [16]. For example, in Japanese macaques, lesions to the posterior region of the left temporal lobe induced greater transient deficits in auditory discrimination of species-typical “coo” calls compared to right hemisphere lesions [27]. In contrast, in rhesus macaques, mainly right hemisphere biased asymmetries were found in cerebral glucose metabolism (measured by positron emission tomography (PET)) in response to species-typical vocalizations within the middle and posterior temporal lobe whereas a significant left hemisphere bias was found in the left temporal pole [28].

In contrast to studies on perception, far fewer studies on asymmetries in the production of species-typical sounds have been conducted. Most well known are the studies by Nottebohm and colleagues in song birds showing that lesions to the left but not right hypoglossal nerve result in significant deficits in song production (reviewed in Nottebohm [29]), though some bird species do show different directional biases in song production [30]–[32]. Leftward biases in sound production have also been reported in frogs [33]. In chimpanzees, population-level right-handedness has been reported for manual gestures [34]. Similar evidence of right-handedness for species-typical gestures has been reported in gorillas [35] and baboons [36].

One behavioral manifestation of the asymmetries in the cortical control of human speech production is the lateralization of oro-facial movements. Specifically, the right side of the mouth moves first and is more expressive when producing words whereas the left half of the mouth is more animated during emotional expression [37]–[40]. Evidence of oro-facial asymmetries in relation to speech production has also been reported in infants, suggesting that left hemisphere asymmetries in linguistically-relevant vocal production are present early in life [41]. Studies of asymmetries in facial expressions associated with the production of species-typical vocalizations in nonhuman primates including marmosets, rhesus monkeys, and chimpanzees have largely reported right hemisphere biased asymmetries, suggesting that, if nonhuman primates follow the human pattern of hemispheric specialization for the production of these types of signals, the sounds and associated facial expressions studied in these species are indicative of emotional valence rather than linguistic or referential information [42]–[45].

Recent studies, however, have demonstrated that captive chimpanzees can learn to voluntarily produce novel sounds to capture the attention of an otherwise inattentive human [46]–[51]. Two such sounds described in chimpanzees are the “raspberry” and “extended grunt” [52]. The raspberry sound (known elsewhere as the ‘splutter’ or the ‘Bronx cheer’) is an unvoiced bilabial trill with a velaric egressive airstream mechanism in which the chimpanzees purse their lips and expel air out from their mouths rather than their lungs, vibrating their lips together to produce sound. van Schaik et al. [53] and, more recently, Cartmill and Byrne [54] have reported that a sound similar to the raspberry is produced in some populations of wild and captive orangutans. The extended grunt is a low frequency but noisy voiced sound that the chimpanzees make with their mouths open while expelling air from the lungs. Although the raspberry has not been described in wild chimpanzees, there is some evidence that the extended grunt has been recorded in wild chimpanzees, at least those at Gombe [55] (p. 131), though only a verbal description has been provided and no spectrogram, so it is not clear if the exact same sound is being produced in wild and captive chimpanzees.

With respect to the function of the raspberry sound and the extended grunt vocalization, several reports have demonstrated that chimpanzees will selectively produce these sounds, and not species-typical food calls, in greater frequency when both food and a human are in proximity to the chimpanzees compared to when only food or only a human are present. In addition, chimpanzees made more species-typical food vocalizations when only food was present but not when only a human was present, or when both food and human were present [46]. These results suggest that chimpanzees are choosing to use the raspberry and extended grunt sounds depending on the presence or absence of a human in conjunction with food. Captive chimpanzees have also been reported to use the raspberry and extended grunt more frequently when a) a human is facing away from them compared to towards them or b) when a human is offering food and looking at a chimpanzee living in the same cage as the focal subject compared to when the human is offering food and looking directly at the focal subject [50]. In contrast to the attention-getting use of the raspberry and extended grunt in captivity, a sound similar to the extended grunt measured in our study is produced by chimpanzees living at Gombe during nesting behavior [55]. Thus, whether the raspberry or extended grunt are observed in wild chimpanzees and other apes remains a topic of interest and continued research. Notwithstanding, it does appear that the functional use of both the raspberry and the extended grunt as an attention-getting mechanism is unique to chimpanzees living in captive environs, suggesting that the chimpanzees have learned to use these sounds in a novel social-cognitive setting.

The differential use of the raspberry and extended grunt in response to orienting or attentional cues of humans, further suggests that these sounds are referential and produced intentionally, in contrast to the majority of primate vocalizations which are widely believed to consist of emotional information and not to be intentionally produced. Because the raspberry is an arbitrary sound, and because both the raspberry and extended grunt have been acquired and are used in different contexts than species-typical calls of chimpanzees [52], in the current study we examined whether facial expressions associated with the production of these sounds were differentially lateralized compared to facial expressions associated with the production of species-typical vocalizations.

For comparison to the raspberry and extended grunt sounds, oro-facial asymmetries associated with two species-typical vocalizations, food-barks and pant-hoots, were measured. These are two vocalizations produced in different emotional contexts by chimpanzees. Food–barks are repeated and often high-pitched barks produced by expelling air from the lungs with the lips slightly parted and mouth corners withdrawn. Food-barks are produced when arriving at food sites or when ingesting highly preferred foods. Pant-hoots are repeated voiced calls consisting of alternating “hoo” vocalizations, produced with forward-protruding rounded lips, and voiced inhalations, during which the mouth is open wide. Pant-hoots are distance calls and are used in several behavioral contexts including when arriving at food sites, when greeting familiar individuals, and during bluff displays [55]. The vast majority of pant-hoots observed in this study were produced during displays directed towards humans or other chimpanzees, a negatively-valenced emotional context. The production of food-barks and pant-hoots in these emotional contexts has been reported in a number of chimpanzee populations both in the wild and in captivity and thus these vocalizations appear to be neither functionally used nor learned in the same way as the raspberry and extended grunt [55], [56].

The oro-facial asymmetry of pant-hoot vocalizations was measured previously by Fernández-Carriba et al. [42] and therefore inclusion of this class of sounds was largely for the purpose of replication of the method. Food-bark vocalizations have not been previously studied but are of interest because they are a positive emotional expression in chimpanzees. Davidson [57] has suggested that positive and negative emotions are differentially produced by the left and right hemispheres, with positive emotions being controlled by the left hemisphere. Fernández-Carriba et al. [42] failed to find evidence of a rightward oro-facial bias for positively-valenced play faces, as would have been predicted by Davidson's hypothesis, but instead found that that play faces were left biased as were negatively-valenced expressions such as the silent bared-teeth and scream face. It is important to note that the play faces that were evaluated by Fernández-Carriba et al. [42] were primarily produced by younger subjects. Thus, including food-barks in this study allowed us to further evaluate the potential role of emotional valence on oro-facial asymmetries in adult chimpanzees. Based on the human pattern of hemispheric dominance in the production of learned, referential signals versus emotional signals, and the failure of Fernández-Carriba et al. [42] to find differential oro-facial lateralization based on emotional valence, we predicted that the raspberry and extended grunt would exhibit a right oro-facial bias suggesting left hemisphere dominant control while the pant-hoot and food-bark would exhibit a left-oro-facial bias suggesting right hemisphere dominant control.

Our findings suggest that chimpanzee facial expressions are differentially expressed on the left and right sides of the face depending on the function of the sounds associated with each expression. Facial expressions associated with the production of raspberry sounds are expressed more intensely on the right side of the face suggesting that the left hemisphere is dominant in the motor control of these novel oro-facial movements. These results are similar to recent findings documenting population-level right-handedness for referential, manual gestures in chimpanzees [34] and more generally suggest that the left hemisphere might control the production of intentionally-produced communicative signals from at least two different sensory modalities in chimpanzees. In contrast, facial expressions associated with involuntary, unlearned, species-typical expressions, including pant-hoots and food-barks, are expressed more intensely on the left side of the face, consistent with the view that they reflect emotional expressions controlled by the right hemisphere.

As an alternative explanation of our results, the observed dichotomy in oro-facial asymmetries may reflect inherent differences between the left and right hemisphere as they relate to motor learning. Clinical and experimental studies suggest that motor movements, particularly complex movements made by the left and right hands, are under the control of the left premotor and supplementary motor areas [58], [59], [60]. Studies also indicate that the left hemisphere, compared to the right, is superior in motor skill acquisition and performance [61]. The raspberry sounds and extended grunt vocalizations used by the chimpanzees in this study are novel and have been acquired through inadvertent instrumental conditioning associated with the prolonged captivity experienced by these animals. The use of these novel, attention-getting sounds and facial expressions and their asymmetric expression on the right side of the face therefore might simply reflect the left hemisphere's superior motor acquisition ability [62] compared to the right, rather than reflect differences in the communicative capacities of the two hemispheres in chimpanzees.

Lastly, it might be suggested that because the raspberry is used in a social context, the right hemi-mouth bias reflects the positive valence effect of the left hemisphere, as has been reported for the “twitter” vocalization in marmosets [44]. We do not favor this explanation for our findings because other facial expressions associated with positive emotional expressions, such as the food-bark from this study and the play face from the study by Fernández-Carriba et al. [42], were found to be expressed more intensely on the left half of the face.

It should be emphasized that we are not suggesting that the chimpanzees have acquired volitional control of their vocalizations per se. The issue of whether nonhuman primates have volitional control of their vocalizations remains a topic of considerable debate [63], [64], [65] and these data do not speak directly to this issue. Recall that the raspberry sound is not a voiced signal but rather it is a sound made by the chimpanzees by expelling air through their lips. Thus, based on these data, we are suggesting that the chimpanzees can learn to manipulate their facial musculature to produce sounds that can be used in specific communicative contexts and that the left hemisphere is dominant in controlling the production of sounds acquired in this manner. From this perspective, it might be further argued that voluntary control of facial expressions may have preceded the evolution of volitional control of the vocal cords and other peripheral structures involved in the production of voiced signals [66], [67], [68], [69].

The presence of left hemisphere specialization in oro-facial motor control in the common ancestor of chimpanzees and humans may have set the stage for the evolution of more sophisticated motor systems including those innervating the tongue and vocal folds that allowed for the emergence of human speech. Arguably one of the initial and important requisite conditions for the emergence of spoken language had to be the ability to learn new sounds and to produce those sounds in functionally-meaningful contexts [63]. Our results suggest that these pivotal abilities may have been present in the common ancestor of humans and chimpanzees.