A Computational Memory and Processing Model for Processing for Prosody

TL;DR

This paper presents LOQ, a text-to-speech model that simulates prosody by incorporating limited attention and working memory, capturing stylistic and individual variations in speech intonation.

Contribution

It introduces a novel computational model linking prosody to attentional and memory constraints, enabling varied and naturalistic speech styles.

Findings

Varying attentional parameters affects prosodic contours.

The model produces multiple prosody styles including child-like and expressive.

Simulations show natural stylistic and individual prosody variations.

Abstract

This paper links prosody to the information in a text and how it is processed by the speaker. It describes the operation and output of LOQ, a text-to-speech implementation that includes a model of limited attention and working memory. Attentional limitations are key. Varying the attentional parameter in the simulations varies in turn what counts as given and new in a text, and therefore, the intonational contours with which it is uttered. Currently, the system produces prosody in three different styles: child-like, adult expressive, and knowledgeable. This prosody also exhibits differences within each style -- no two simulations are alike. The limited resource approach captures some of the stylistic and individual variety found in natural prosody.