Interacting with Global Content

Interacting with Global Content

This research activity allows people to interact with digital content in ways that are more intuitive and that mimic the richness of human perception in all interaction. This research goes beyond text and speech-based exchange of content, to full multimodal interfaces that interpret information from a multitude of audio and visual cues. By furthering both the understanding and automatic analysis of human interaction with digital content and other humans, we are transforming the retrieval, understanding, and delivery of multimodal content for users.

In driving a more complete understanding of multimodal interaction between humans and for humans with digital content, we build automatic systems that track human engagement and affective response, and judge how best to retrieve and render responsive content for the user.

Research team

Publications

Conference

Object Geolocation from Crowdsourced Street Level Imagery 

  • Posted: 14 Jul 2019
  • Author: , R. Dahyot, V. Krylov
  • Publication: UrbReas 2018 - International Workshop on Urban Reasoning in conjunction with the European Conference on Machine Learning and Pri
Interacting with Global Content

Perception & Perspective: An Analysis of Discourse and Situational Factors in Reference Frame Selection

  • Posted: 15 Jun 2018
  • Author: Robert Ross, Kavita Thomas
  • Publication: DAP 2018 - Workshop on Dialogue and Perception
Conference

A Multi-Task Approach to Incremental Dialogue State Tracking

  • Posted: 10 Sep 2018
  • Author: Robert Ross, John D. Kelleher, Anh Duong Trinh
  • Publication: SemDial 2018 - 22nd workshop on the Semantics and Pragmatics of Dialogue
Interacting with Global Content

Can DNNs Learn to Lipread Full Sentences?

  • Posted: 1 Oct 2018
  • Author: George Sterpu, Christian Saam, Naomi Harte
  • Publication: ICIP 2018 - 25th IEEE International Conference on Image Processing

Research Goals

New methods are being developed to process both speech-only and audio-visual data, and train statistical engines to infer attentional state. The ability to track user engagement and interest in conversational interaction is key to reproducing natural interactions in the future, be that with a robot, personal assistant or avatar. The research explores what makes an avatar, or computer generated speaker, engaging to a user. The research uniquely combines ADAPT expertise on expressive synthesis, the role of paralinguistic cues in speech, and avatar animation.

Also addressed are issues of multimodal content relevant to interaction from two perspectives: The first addresses challenges of locating and isolating objects of interest in a visual stream and exploiting visual cues in speech to augment speech recognition capabilities. Learning techniques from unstructured multimodal data streams are also examined. The second is addressed by establishing methods for the exploitation of dialogue in user interaction in information retrieval, and to the exploitation of context to enable proactive information retrieval.

Twitter
10 am
@Adaptcentre
They’ve made it to Basecamp! Well done @seamuslawless @IrelandOnEverest Onwards and upwards! pic.twitter.com/Nxdk7PRJuo

Newsletter

Sign up to our newsletter for all the latest updates on ADAPT news, events and programmes.
Archived newsletters can be viewed here.