Expressivity and Speech Synthesis
MCML Authors
Andreas Triantafyllopoulos
Dr.
Björn Schuller
Prof. Dr.
Core PI
Abstract
Andreas Triantafyllopoulos
Dr.
Björn Schuller
Prof. Dr.
Core PI
Abstract
Imbuing machines with the ability to talk has been a longtime pursuit of artificial intelligence (AI) research. From the very beginning, the community has not only aimed to synthesize high-fidelity speech that accurately conveys the meaning of an utterance, but also to color it with inflections that cover the same range of affective expressions that humans are capable of, with recent advances yielding impressive results. This chapter outlines the methodological advances that brought us so far and sketches out the ongoing efforts to reach that coveted next level of artificial expressivity. It also discusses the societal implications coupled with rapidly advancing expressive speech synthesis (ESS) technology and highlights ways to mitigate those risks and ensure the alignment of ESS capabilities with ethical norms.
article TS26
Oxford Handbook of Expressivity in Language
IV.41. Jan. 2026.Authors
A. Triantafyllopoulos • B. W. SchullerLinks
DOIResearch Area
BibTeXKey: TS26