Towards the generation of dialogue acts in socio-affective ECAs: a corpus-based prosodic analysis

Abstract

International audienceWe present a corpus-based prosodic analysis with the aim of uncovering the relationship between dialogue acts, personality and prosody in view to providing guidelines for the ECA Greta's text-to-speech system. The corpus used is the SEMAINE corpus, featuring four different personalities, further annotated for dialogue acts and prosodic features. In order to show the importance of the choice of dialogue act taxonomy, two different taxonomies were used, the first corresponding to Searle's taxonomy of speech acts and the second, inspired by Bunt's DIT++, including a division of directive acts into finer categories. Our results show that finer-grained distinctions are important when choosing a taxonomy. We also show with some preliminary results that the prosodic correlates of dialogue acts are not always as cited in the literature and prove more complex and variable. By studying the realisation of different directive acts, we also observe differences in the communicative strategies of the ECA depending on personality, in view to providing input to a speech system

An Optimality‐Theoretic Analysis of the Acquisition of English Sentence Stress Based on Acoustic Data

“…e first constraint is DEP-IO (P), which is violated when the generally unstressed words are accented, especially with contrastive or emphatic information or by misplacement of stress. In such situation, all prominence achieved in the output may be more than that in the input [23]. In the given material, violations of DEP-IO (P) were opposite in sentence 1; hello and she in sentence 2; did in sentence 3; up in sentence 4; why in sentence 5; myself in sentence 6; who and that in sentence 8; and I in sentence 9.…”