Prof. Woodland’s research is in the area on speech and language technology with a major focus on developing all aspects of speech recognition systems.

His group has developed a number of techniques in that have been widely used in large vocabulary systems including standard methods for transform-based adaptation and discriminative sequence training. He has worked on the use of deep neural networks for both acoustic models and language models. His current work has a focus on the use and development of end-to-end trainable neural network systems. One area of interest is developing flexible systems that can adapt to a wide range of speakers, acoustic conditions, speaking style, language, task etc., with relatively limited training resources. This includes work on unsupervised training, active learning and self-supervised learning, the use of speech and text data for adapting models, as well as contextual speech recognition for biasing neural models. He is also interested in areas including speaker diarisation (who spoke when), emotion recognition from speech data, processing highly overlapped data, multimodal data (speech and video), optimisation techniques large for large sequence-to-sequence models models and confidence estimation.

He is well known for his work on the HTK large vocabulary speech recognition systems.

He has also worked on audio indexing, machine translation from speech, keyword spotting, auditory modelling and speech synthesis.