ADAPT researchers successfully organized the UK Speech Conference 2018, an event which assembles leading researchers from the UK and Ireland’s Speech Science and Technology community to share their ongoing research. The event, sponsored by Google and Amazon, was coordinated by ADAPT’s forefront specialists in human and machine speech and technology Prof Naomi Harte, Dr. Joao Cabral, Dr. Wissam Jassim, and Dr. Ilaria Torre.
The conference was held from June 25th-26th at the Hamilton Conference Centre in Trinity College Dublin, with participants elaborating on their research in Speech Science and Technology related topics such as speech synthesis, speech coding, and human-machine communication.
Three keynote speakers delivered seminars highlighting distinct aspects of the human and machine speech field. Professor Patricia Scanlon, founder, and CEO of Soapbox Labs gave a talk titled Children’s Speech Recognition – From the Lab to the Living Room where she elaborated on Soapbox’s innovative children’s voice technology platform which tackled the discrepancy between adult and child voice interface quality. Professor Roger Moore of the University of Sheffield presented on Spoken Language Processing: Are We Nearly There Yet?, and Professor Stavros Petridis of Imperial College London discussed Deep Learning for End-to-End Audio-Visual Speech Recognition, a proposal to integrate visual information, such as the monitoring of lip movements, to enhance the performance of acoustic speech recognition systems in noise filled environments.
In addition to insightful keynotes, ADAPT Ph.D. Student Matthew Roddy delivered a talk based on the paper he co-authored with Naomi Harte, titled Multimodal Continuous Turn-Taking Prediction Using Multiscale RNNs. ADAPT is delighted to be represented at the leading UK and Ireland Speech Conference with four posters highlighting the work from within the team.
– Voice Activity Detection Using Neurograms; Wissam Jassim, Naomi Harte
– Mismatched audio-video smiling in an avatar and its effect on trust; Ilaria Torre, Emma Carrigan, Killian McCabe, Rachel McDonnell, Naomi Harte
– Progress on Lip-Reading Sentences; George Sterpu, Christian Saam, Naomi Harte
– The State of Speech in HCI: Trends, Themes, and Challenges; Leigh Clark, Phillip Doyle, Diego Garaialde, Emer Gilmartin, Stephan Schlögl, Jens Edlund, Matthew Aylett, João Cabral, Cosmin Munteanu, Benjamin Cowan
– Estimation of the asymmetry parameter of the glottal flow waveform using the Electroglottographic signal; João Cabral
To find more information from the UK Speech Conference 2018, please visit their website. http://kalman.mee.tcd.ie/ukspeech2018/
Share this article: