Salil Deena

According to our database, Salil Deena authored at least 14 papers between 2009 and 2019.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2019

Recurrent Neural Network Language Model Adaptation for Multi-Genre Broadcast Speech Recognition and Alignment.

Salil Deena, Madina Hasan, Mortaza Doulaty, Oscar Saz, Thomas Hain

IEEE ACM Trans. Audio Speech Lang. Process., 2019

Unsupervised Adaptation of Acoustic Models for ASR Using Utterance-Level Embeddings from Squeeze and Excitation Networks.

Hardik B. Sailor, Salil Deena, Md Asif Jalal, Rasa Lileikyte, Thomas Hain

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2018

Lightly supervised alignment of subtitles on multi-genre broadcasts.

Oscar Saz, Salil Deena, Mortaza Doulaty, Madina Hasan, Bilal Khaliq, Rosanna Milner, Raymond W. M. Ng, Julia Olcoz, Thomas Hain

Multim. Tools Appl., 2018

Improving ASR Error Detection with RNNLM Adaptation.

Rahhal Errattahi, Salil Deena, Asmaa El Hannani, Hassan Ouahmane, Thomas Hain

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

2017

Semi-Supervised Adaptation of RNNLMs by Fine-Tuning with Domain-Specific Auxiliary Features.

Salil Deena, Raymond W. M. Ng, Pranava Swaroop Madhyastha, Lucia Specia, Thomas Hain

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

Exploring the use of acoustic embeddings in neural machine translation.

Salil Deena, Raymond W. M. Ng, Pranava Swaroop Madhyastha, Lucia Specia, Thomas Hain

Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

2016

webASR 2 - Improved Cloud Based Speech Technology.

Thomas Hain, Jeremy Christian, Oscar Saz, Salil Deena, Madina Hasan, Raymond W. M. Ng, Rosanna Milner, Mortaza Doulaty, Yulan Liu

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Combining Feature and Model-Based Adaptation of RNNLMs for Multi-Genre Broadcast Speech Recognition.

Salil Deena, Madina Hasan, Mortaza Doulaty, Oscar Saz, Thomas Hain

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

2015

The 2015 sheffield system for transcription of Multi-Genre Broadcast media.

Oscar Saz, Mortaza Doulaty, Salil Deena, Rosanna Milner, Raymond W. M. Ng, Madina Hasan, Yulan Liu, Thomas Hain

Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

The 2015 sheffield system for longitudinal diarisation of broadcast media.

Rosanna Milner, Oscar Saz, Salil Deena, Mortaza Doulaty, Raymond W. M. Ng, Thomas Hain

Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

2013

Visual Speech Synthesis Using a Variable-Order Switching Shared Gaussian Process Dynamical Model.

Salil Deena, Shaobo Hou, Aphrodite Galata

IEEE Trans. Multim., 2013

2012

Visual speech synthesis by learning joint probabilistic models of audio and video.

Salil Prashant Deena

PhD thesis, 2012

2010

Visual speech synthesis by modelling coarticulation dynamics using a non-parametric switching state-space model.

Salil Deena, Shaobo Hou, Aphrodite Galata

Proceedings of the 12th International Conference on Multimodal Interfaces / 7. International Workshop on Machine Learning for Multimodal Interaction, 2010

2009

Speech-Driven Facial Animation Using a Shared Gaussian Process Latent Variable Model.

Salil Deena, Aphrodite Galata

Proceedings of the Advances in Visual Computing, 5th International Symposium, 2009