Humane Speech Synthesis through Zero-Shot Emotion and Disfluency Generation

arXiv:2404.01339v1 Announce Type: new
Abstract: Contemporary conversational systems often present a significant limitation: their responses lack the emotional depth and disfluent characteristic of human interactions. This absence becomes particularly noticeable when users seek more personalized and empathetic interactions. Consequently, this makes them seem mechanical and less relatable to human users. Recognizing this gap, we embarked on a journey to humanize machine communication, to ensure AI systems not only comprehend but also resonate. To address this shortcoming, we have designed an …

abstract arxiv conversational cs.ai cs.cl cs.hc emotion human humane human interactions interactions personalized responses speech synthesis systems them through type zero-shot