Speech Technology
The Speech Technology Group (STG) is at the heart of modern artificial intelligence by designing novel algorithms for automatic speech recognition and data-based dialogue systems enabling the creation of advanced and natural, speech enabled, human-machine interfaces.
In that context, our target is to create new products and services that facilitate the access of information and the creation of knowledge effectively, for improving productivity and quality of life.
STG has made significant contributions to the next generation of Toshiba’s speech recognition and HMM-based speech synthesis. In addition to core underlying technology, the STG has developed speech technology for the major North American and European languages. We work in collaboration with the speech R&D groups at the Knowledge Media Lab, Toshiba RDC, Kawasaki, Japan and Toshiba China R&D Center, Beijing, China, and business divisions of Toshiba Group, Japan.
Working with groups within Toshiba, we have a tight coupling between our R&D efforts and current and future product development. This enables us to ensure that our research work will be of direct practical benefit. We fund research and have academic collaborations with groups in various UK and European Union Universities and Research Centers. Combining the strengths of our group with these collaborations, we address various research topics for the future.
Automatic Speech Recognition ►
Latest Publications
Learning Noise Invariant Features through Transfer Learning for Robust End-to-End Speech Recognition
S. Zhang, C.-T. Do, R. Doddipatla and S. Renals
Accepted for publication at IEEE ICASSP 2020, Barcelona, Spain, May 2020
On End-to-End Multi-Channel Time Domain Speech Separation in Reverberant Environments
J. Zhang, T.C. Zorila, R. Doddipatla and J. Barker
Accepted for publication at IEEE ICASSP 2020, Barcelona, Spain, May 2020
Robust Belief State Space Representation for Statistical Dialogue Managers using Deep Autoencoders
F. Lygerakis, V. Diakoloulas, M. Lagoudakis and M. Kotti
Proc. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU2019), Sentosa, Singapore, December 2019
An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription
T.C. Zorila, C. Boeddeker, R. Doddipatla and R. Haeb-Umbach
Proc. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU2019), Sentosa, Singapore, December 2019 / arXiv / free
Crowd-sourced Collection of Task-Oriented Human-Human Dialogues in a Multi-Domain Scenario
N. Braunschweiler, P. Papadakos, M. Kotti, Y. Marketakis and Y. Tzitzikas
Proc. International Conference on Text, Speech and Dialogue (TSD2019), Ljubljana, Slovenia, September 2019