The Role of Vocal Persona in Natural and Synthesized Speech

TL;DR

This paper explores how vocal persona influences synthesized speech, proposing a framework for context-dependent voice expression and analyzing expert insights to enhance human-computer interaction applications.

Contribution

It introduces a novel framework for embedding contextually-dependent vocal personas in speech synthesis systems, informed by expert interviews.

Findings

Identified key themes from expert interviews on vocal persona

Framework enables dynamic, context-aware voice modulation

Initial results suggest improved naturalness and expressiveness

Abstract

The inclusion of voice persona in synthesized voice can be significant in a broad range of human-computer-interaction (HCI) applications, including augmentative and assistive communication (AAC), artistic performance, and design of virtual agents. We propose a framework to imbue compelling and contextually-dependent expression within a synthesized voice by introducing the role of the vocal persona within a synthesis system. In this framework, the resultant 'tone of voice' is defined as a point existing within a continuous, contextually-dependent probability space that is traversable by the user of the voice. We also present initial findings of a thematic analysis of 10 interviews with vocal studies and performance experts to further understand the role of the vocal persona within a natural communication ecology. The themes identified are then used to inform the design of the aforementioned framework.