Let's talk about "talking" dogs! Reviewing the science behind a bold idea

Abstract

The concept of a "talking" dog has long fascinated humans, as presented throughout history in pieces of folklore, literature, and other fields of culture. While speech, as we know, is a uniquely human trait, the evolution of dogs in close proximity to humans has allowed them to develop strategies that facilitate heterospecific communication with us. In this work, we explore the scientific plausibility of enhancing canine vocalisation towards speech-like communication, as Csányi (Bukfenc és Jeromos: hogyan gondolkodnak a kutyák? Vince K, 2001) suggested. Our approach involves a comprehensive overview of the anatomical, cognitive, and evolutionary features of dogs that may relate to speech, as well as describing their role in popular culture and examining novel technological aspects. We also provide an outlook on hypothetical possibilities of a "talking" dog and its possible implications. We conclude that while dogs have acquired remarkable human-directed social and communicative skills, the feasibility and desirability of spoken language in dogs remain questionable. Instead, understanding canine vocal and non-vocal communication within the context of human-animal interaction provides valuable insights into both language evolution and the mechanisms underpinning interspecies cooperation, also providing practical tools for the novel field of ethorobotics.

Keywords: Dog; Ethorobotics; Heterospecific communication; Social cognition; Speech; Vocal communication.

Fig. 1

Sample from a “talking” dog video (https://youtu.be/HrO6LbXLu_I?si=DEPg6Xr72d6d_ogx&t=36) showing a French bulldog saying “I love you”. The top part shows the oscillogram representing the raw waveform of the sound; the middle is a sonogram showing the change of the sound’s power-spectrum over time optimised for frequency resolution (the greyscale colouring shows the power of a given frequency component: the darker a spot, the higher the power is), with highlighted pitch contours (cyan: female human, blue: dog utterances); the bottom is also a sonogram optimised for highlighting the formant structure (only the first three formants are highlighted; orange: female human, red: dog utterances). Note the similar height of the fundamental frequency (on average 275 Hz for the human and for the dog 431 Hz including, while 368 Hz excluding the high-pitched initial call), the similar harmonic structure (energy loss in the above 3000 Hz in the spectrum of the dog vocalisation is probably due to the distance difference from the microphone). While consonants are practically missing from the dog's utterance, vowel-like parts are similar to human speech sounds. The dog’s “I” [aɪ] sound is a bark-like short call; its fundamental and first formant falls in the same area as the human “I” [aɪ]’s first two formants. In the case of the “o” [ʌ] sound, the spectral similarity is remarkable. However, the closing “ou” [u:]’s formant structure differs greatly from the human version