Intentionality in Speech: Implications for Computational Models

The field of spoken language processing typically treats speech as classic stimulus-response behaviour, hence there is strong interest in using the latest machine learning techniques (such as Deep Neural Networks) to estimate the assumed non-linear transforms. However, in reality, speech is not a static process - rather it is a sophisticated joint behaviour resulting from actively managed dynamic coupling between speakers, listeners and their respective environmental contexts. Multiple layers of feedback control play a crucial role in maintaining the necessary communicative stability, and this means that there are significant dependencies that are overlooked in contemporary SLP approaches. This talk will address these issues in the wider context of intentional behaviour, and will give an insight into the implications for computational models.