Projects per year
Ben Milner received a PhD in robust speech processing from the University of East Anglia in 1995. Prior to this he received a BEng in electronic engineering
In 1994 Ben moved to BT Laboratories in the speech recognition group, where he specialised in noise and channel robustness and front-end processing. In particular he worked on reducing error rates for services such as automated directory enquiries and speech recognition from payphones. More recent work at BT considered the effect of performing speech recognition over mobile and IP networks where problems of packet loss and codec distortion are addressed. He was also responsible for the handwriting component of BT's SmartQuill which features in the Guinness Book of Records as 'the world's most intelligent pen!'. He was also involved in work to automatically detect the internal rotting of telephone poles. He holds three patents in the areas of speech processing and handwriting recognition.
In March 2001 Ben returned to the School of Information Systems (now the School of Computing Sciences) as a Senior Lecturer.
Ben has also spent some time in oil and gas exploration working on side scan sonar and seabed profiling.
- Guest editor: special edition of Speech Communication and Robustness Issues for Conversation Interaction, 2006
- Chairman: ISCA Tutorial and Research Workshop (ITRW) Robust2004-Robustness Issues for Conversation Interaction-UEA, 2004
Key Research Interests and Expertise
Ben Milner is part of the Speech, Language and Audio Processing
Ben's research interests continue to be in the area of robust speech processing. In particular considering the effects of mobile and IP networks on speech quality and recognition performance.
Milner, B. P. and Shao, X., Prediction of Fundamental Frequency and Voicing from Mel-Frequency Cepstral Coefficients for Unconstrained Speech Reconstruction. IEEE Transactions on Audio, Speech and Language Processing, Volume 15, Issue 1, Page(s) 24-33, 2007.
Darch, J., Milner, B.P., and Saeed Vaseghi, MAP Prediction of Formant Frequencies and Voicing Class from MFCC Vectors in Noise. Speech Communication, Volume 48, Issue 11, Page(s) 1556-1572, 2006.
James, A. B. and Milner, B. P., Towards improving the robustness of distributed speech recognition in packet loss. Journal of Speech Communication, Volume 48, Issue 11, Page(s) 1402-1421, 2006.
Milner, B. P. and James, A. B., Robust speech recognition over mobile and IP networks in burst-like packet loss. IEEE Trans. Audio, Speech and Language Processing, Volume 14, Issue 1, Page(s) 223-231, 2006.
Associate Dean for Learning and Teaching, Faculty of Science
Director of Learning and Teaching, School of Computing Sciences
Dive into details
Select a country/territory to view shared publications and projects
1/04/21 → 31/03/23
1/04/21 → 31/03/23
Lettice, F., Aung, M. H., Bagnall, T., Buckley, O., Cawley, G., Day, A., De La Iglesia, B., Finlayson, G., Harvey, R., Huber, K., Kulinskaya, E., Laycock, S., Lines, J., Mackiewicz, M., Milner, B., Moulton, V., Parr, G., Ren, E. & Wang, W.
10/01/20 → 8/01/22
6/01/20 → 10/07/20
Improving the robustness of right whale detection in noisy conditions using denoising autoencoders and augmented trainingVickers, W., Milner, B. & Lee, R., 13 May 2021. 5 p.
Research output: Contribution to conference › PaperOpen AccessFile5 Downloads (Pure)
Vickers, W., Milner, B., Risch, D. & Lee, R., Jun 2021, In : Journal of the Acoustical Society of America. 149, 6, p. 3797-3812 16 p., 3797.
Research output: Contribution to journal › Article
Websdale, D., Taylor, S. & Milner, B., 14 Jun 2021, In : IEEE Transactions on Multimedia.
Research output: Contribution to journal › ArticleOpen AccessFile4 Downloads (Pure)
Vickers, W., Milner, B., Gorpincenko, A. & Lee, R., 2020, EUSIPCO 2020.
Research output: Chapter in Book/Report/Conference proceeding › Conference contributionOpen AccessFile6 Downloads (Pure)
A comparison of machine learning methods for detecting right whales from autonomous surface vehiclesVickers, W., Milner, B., Lee, R. & Lines, J., 18 Nov 2019, p. 1-5. 5 p.
Research output: Contribution to conference › PaperOpen AccessFile1 Citation (Scopus)35 Downloads (Pure)