As we are trying to find short sequences of conversation that can be turned into useful training material for cochlear implant users we thought it may be helpful to get a wider perspective on how speakers take turns in conversation. We would like to see how other people are studying turn exchange between speakers in conversations and how they are applying existing knowledge in their own work. So, we decided to organise a workshop, invite researchers from different disciplines to discuss turn-taking in some of the conversations in our corpus, and learn from them.
Our free one-day workshop Turn-taking in conversation: a multi-disciplinary approach will take place on 9th July 2014 in Humanities Research Institute (HRI) at the University of Sheffield. It will feature two invited talks on turn-taking from an interactional linguistic perspective and an applied perspective of computational processing of conversational speech. We will then have an afternoon of group exercises in conversation analysis of talk and a closing panel discussion. We hope to meet people from other disciplines, have great discussions and gain important insights on turn-taking practices in conversation that will help us in our data selection and software development.
For more information and how to register please see the workshop website.
The workshop is supported by iCog Network
I was very pleased to attend the Voice Measurement & Applications workshop last week, held in London in the Speech, Hearing and Phonetic Sciences department at UCL. The workshop revealed how recent advances in audio, signal processing and machine learning are producing new applications of voice measurement. Many interesting projects were presented, and existing challenges in these fields were discussed.
Although it is not straightforward to design appropriate conversation training tasks, I felt proud that our Overlap project is working with real conversational material rather than isolated units of speech. Extended vowel phonations have commonly been used in clinical applications (for instance, asking someone diagnosed with Parkinsons to say ‘aaaaaah’). The simplification of diagnostic speech material was criticised during the workshop, however, and further to this, Dr Elina Tripoliti showed that it sometimes led to measures of voice quality which contradicted measures of real connected speech.
The workshop primarily addressed the topic of accurately measuring acoustic characteristics of the voice, assessing its quality, and tracking its changes over time. Our Overlap project is rather wider in scope, however. We do address topics of voice production, nonetheless we are more directly concerned with the communicative difficulties that cochlear-implant users face in day-to-day situations.