Salil Deena

Past Members, Researchers, VoiceBase

I am a Research Associate in the SpandH group and working on the EPSRC project: “Natural Speech Technology”. I gained a PhD in Computer Science from the University of Manchester with a thesis on visual speech synthesis, awarded in 2012. From 2012 to 2014, I worked as Research Engineer at Image Metrics researching Computer vision and Machine Learning techniques for facial analysis and animation. My research interests are in probabilistic models and their applications to speech recognition and synthesis.

Publications

2019

Salil Deena; Madina Hasan; Mortaza Doulaty; Oscar Saz; Thomas Hain: Recurrent Neural Network Language Model Adaptation for Multi-Genre Broadcast Speech Recognition and Alignment. In: IEEE ACM Trans. Audio Speech Lang. Process., vol. 27, no. 3, pp. 572–582, 2019. (Type: Journal Article | Links)

Hardik B. 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. In: IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019, Singapore, December 14-18, 2019, pp. 980–987, IEEE, 2019. (Type: Proceedings Article | Links)

2018

Oscar Saz; Salil Deena; Mortaza Doulaty; Madina Hasan; Bilal Khaliq; Rosanna Milner; Raymond W. M. Ng; Julia Olcoz; Thomas Hain: Lightly supervised alignment of subtitles on multi-genre broadcasts. In: Multim. Tools Appl., vol. 77, no. 23, pp. 30533–30550, 2018. (Type: Journal Article | Links)

Rahhal Errattahi; Salil Deena; Asmaa El Hannani; Hassan Ouahmane; Thomas Hain: Improving ASR Error Detection with RNNLM Adaptation. In: 2018 IEEE Spoken Language Technology Workshop, SLT 2018, Athens, Greece, December 18-21, 2018, pp. 190–196, IEEE, 2018. (Type: Proceedings Article | Links)

2017

Salil Deena; Raymond W. M. Ng; Pranava Swaroop Madhyastha; Lucia Specia; Thomas Hain: Exploring the use of acoustic embeddings in neural machine translation. In: 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017, Okinawa, Japan, December 16-20, 2017, pp. 450–457, IEEE, 2017. (Type: Proceedings Article | Links)

Salil Deena; Raymond W. M. Ng; Pranava Swaroop Madhyastha; Lucia Specia; Thomas Hain: Semi-Supervised Adaptation of RNNLMs by Fine-Tuning with Domain-Specific Auxiliary Features. In: Lacerda, Francisco (Ed.): Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017, pp. 2715–2719, ISCA, 2017. (Type: Proceedings Article | Links)

2016

Thomas Hain; Jeremy Christian; Oscar Saz; Salil Deena; Madina Hasan; Raymond W. M. Ng; Rosanna Milner; Mortaza Doulaty; Yulan Liu: webASR 2 - Improved Cloud Based Speech Technology. In: Morgan, Nelson (Ed.): Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016, pp. 1613–1617, ISCA, 2016. (Type: Proceedings Article | Links)

Salil Deena; Madina Hasan; Mortaza Doulaty; Oscar Saz; Thomas Hain: Combining Feature and Model-Based Adaptation of RNNLMs for Multi-Genre Broadcast Speech Recognition. In: Morgan, Nelson (Ed.): Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016, pp. 2343–2347, ISCA, 2016. (Type: Proceedings Article | Links)

2015

Heidi Christensen; Mauro Nicolao; Stuart P. Cunningham; Salil Deena; Phil D. Green; Thomas Hain: Speech-Enabled Environmental Control in an AAL setting for people with Speech Disorders: a Case Study. In: IET International Conference on Technologies for Active and Assisted Living, TechAAL 2015, London, UK, 2015. (Type: Proceedings Article | )

Oscar Saz; Mortaza Doulaty; Salil Deena; Rosanna Milner; Raymond W. M. Ng; Madina Hasan; Yulan Liu; Thomas Hain: The 2015 sheffield system for transcription of Multi-Genre Broadcast media. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015, pp. 624–631, IEEE, 2015. (Type: Proceedings Article | Links)

Rosanna Milner; Oscar Saz; Salil Deena; Mortaza Doulaty; Raymond W. M. Ng; Thomas Hain: The 2015 sheffield system for longitudinal diarisation of broadcast media. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015, pp. 632–638, IEEE, 2015. (Type: Proceedings Article | Links)