Comparing alignment toward American, British, and Indian English text-to-speech (TTS) voices: influence of social attitudes and talker guise

Text-to-speech (TTS) voices, which vary in their apparent native language and dialect, are increasingly widespread. In this paper, we test how speakers perceive align toward TTS voices that represent American, British, Indian dialects of English the extent social attitudes shape patterns convergence divergence. We also whether top-down knowledge talker, manipulated as a “human” or “device” guise, mediates these accommodation. Forty-six American English-speaking participants completed identical interactions with 6 talkers (2 from each dialect) rated talker on variety factors. Accommodation was assessed AXB perceptual similarity by separate group raters. Results show had strongest positive converged them more. Conversely, rate less human-like diverge them. Finally, overall more accommodation were presented guise. discuss results through lens Communication Theory (CAT).