Publications

Conferences/Workshops

• Hardik Sailor, Salil Deena, Md Asif Jalal, Rasa Lileikyte, Thomas Hain, "Unsupervised Adaptation of Acoustic Models for ASR using Utterance-level Embeddings from Squeeze and Excitation Networks", ASRU'19: IEEE Workshop on Automatic Speech Recognition and Understanding, Singapore, 2019 paper

• Rahhal Errattahi, Salil Deena, Asmaa El Hannani, Hassan Ouahmane, Thomas Hain, "Improving ASR Error Detection with RNNLM Adaptation", SLT'18: IEEE Workshop on Spoken Language Technology, Athens, Greece, 2018 paper poster

• Salil Deena, Raymond Ng, Pranava Madhyashtha, Lucia Specia and Thomas Hain, "Exploring the use of Acoustic Embeddings in Neural Machine Translation", ASRU'17: IEEE Workshop on Automatic Speech Recognition and Understanding, Okinawa, Japan, 2017 paper poster

• Salil Deena, Raymond Ng, Pranava Madhyashtha, Lucia Specia and Thomas Hain, "Semi-supervised Adaptation of RNNLMs by Fine-tuning with Domain-specific Auxiliary Features", ISCA Interspeech, Stockholm, Sweden, 2017 paper slides

• Salil Deena, Madina Hasan, Mortaza Doulaty, Oscar Saz and Thomas Hain, "Combining Feature and Model-Based Adaptation of RNNLMs for Multi-Genre Broadcast Speech Recognition", ISCA Interspeech, San Francisco, CA, USA, 2016 paper slides data

• Thomas Hain, Jeremy Christian, Oscar Saz, Salil Deena, Raymond Ng, Rosanna Milner, Madina Hasan, Mortaza Doulaty and Yulan Liu, "webASR 2 - Improved cloud based speech technology", ISCA Interspeech, San Francisco, CA, USA, 2016 paper website

• Rosanna Milner, Oscar Saz, Salil Deena, Mortaza Doulaty, Raymond Ng, and Thomas Hain, “The 2015 Sheffield System for Longitudinal Diarisation of Broadcast Media”,  ASRU'15: Proc. of the IEEE Workshop on Automatic Speech Recognition and Understanding, Scottsdale, AZ, USA, 2015 paper

• Oscar Saz, Mortaza Doulaty, Salil Deena, Rosanna Milner, Raymond Ng, Madina Hasan, Yulan Liu, and Thomas Hain, “The 2015 Sheffield System for Transcription of Multi–Genre Broadcast Media”, ASRU'15: Proc. of the IEEE Workshop on Automatic Speech Recognition and Understanding, Scottsdale, AZ, USA, 2015 paper

• Heidi Christensen, Mauro Nicolao, Stuart Cunningham, Salil Deena, Phil Green, and Thomas Hain, “Speech-Enabled Environmental Control in an AAL setting for people with Speech Disorders: a Case Study”, TechAAL'15: Proc of the IET International Conference on Technologies for Active and Assisted Living, London, UK, 2015, pp. 1-6 paper

• Salil Deena, Shaobo Hou and Aphrodite Galata, "Visual Speech Synthesis by Modelling Coarticulation Dynamics using a Non-Parametric Switching State-Space Model", ICMI-MLMI'10: Proc. of the ACM International Conference on Multimodal Interfaces and Workshop on Machine Learning for Multimodal Interaction, Beijing, China, 2010 paper slides poster

• Salil Deena and Aphrodite Galata, "Speech-Driven Facial Animation Using a Shared Gaussian Process Latent Variable Model", ISVC'09: Proc. of International Symposium on Visual Computing, Las Vegas, NV, USA, 2009 paper slides poster

Posters

• Salil Deena, "The Sheffield System for Airbus Air Traffic Control Speech Recognition Challenge 2018", IRIT/SAMOVA Airbus ATC Challenge Workshop, Toulouse, France, 2018 poster

• Salil Deena, Raymond Ng, Pranava Madhyashtha, Lucia Specia and Thomas Hain, "Exploring the use of Acoustic Embeddings in Neural Machine Translation", UK Speech, Dublin, Ireland, 2018 abstract poster

• Salil Deena, Raymond Ng, Pranava Madhyashtha, Lucia Specia and Thomas Hain, "Semi-supervised Adaptation of RNNLMs by Fine-tuning with Domain-specific Auxiliary Features", UK Speech, Cambridge, UK, 2017 abstract poster

• Salil Deena, Madina Hasan, Mortaza Doulaty, Oscar Saz and Thomas Hain, "Combining Feature and Model-Based Adaptation of RNNLMs for Multi-Genre Broadcast Speech Recognition", UK Speech, Sheffield, UK, 2016 abstract poster

• Martin de La Gorce, Salil Deena, Tomos Williams, Mike Rogers and Kevin Walker, "Real-time Video-based Character Animation", CVMP'12: European Conference on Visual Media Production, London, UK, 2012 abstract poster

Journals

• Salil Deena, Madina Hasan, Mortaza Doulaty, Oscar Saz and Thomas Hain, "Recurrent Neural Network Language Model Adaptation for Multi-Genre Broadcast Speech Recognition and Alignment", IEEE/ACM Transactions on Audio, Speech and Language Processing, 27(3): 572-582, 2019 paper data

• Oscar Saz, Salil Deena, Mortaza Doulaty, Madina Hasan, Bilal Khaliq, Rosanna Milner, Raymond Ng, Julia Olcoz and Thomas Hain: "Lightly supervised alignment of subtitles on multi-genre broadcasts", Multimedia Tools and Applications, 77(23): 30533-30550, 2018 paper data

• Salil Deena, Shaobo Hou and Aphrodite Galata, "Visual Speech Synthesis using a Variable-Order Switching Shared Gaussian Process Dynamical Model", IEEE Transactions on Multimedia, 15(8):1755-1768, 2013 paper

Patents

• Kevin Walker, Michael Rogers, Tomos Williams, Salil Deena, "Monetization using video-based simulation of cosmetic products", United States Patent 9460462 B1, 2016 link

• Michael Rogers, Tomos Williams, Kevin Walker, Salil Deena, "Building systems for adaptive tracking of facial features across individuals and groups", United States Patent 9104908 B1, 2015 link

Theses

• Salil Deena, "Visual Speech Synthesis by Learning Joint Probabilistic Models of Audio and Video", PhD Thesis, School of Computer Science, The University of Manchester, 2012 link slides

• Salil Deena, "Probabilistic Methods for Videorealistic Speech Animation", MSc Thesis, School of Computer Science, The University of Manchester, 2007 link