Salil Deena

14 papers A 3C 4Journal 4Unranked 3
YearRankTypeTitle / Venue / Authors
2019 J jnl
Recurrent Neural Network Language Model Adaptation for Multi-Genre Broadcast Speech Recognition and Alignment.
IEEE ACM Trans. Audio Speech Lang. Process.
Salil Deena, Madina Hasan, Mortaza Doulaty, Oscar Saz, Thomas Hain
2019 C conf
Unsupervised Adaptation of Acoustic Models for ASR Using Utterance-Level Embeddings from Squeeze and Excitation Networks.
ASRU
Hardik B. Sailor, Salil Deena, Md Asif Jalal, Rasa Lileikyte, Thomas Hain
2018 — conf
Improving ASR Error Detection with RNNLM Adaptation.
SLT
Rahhal Errattahi, Salil Deena, Asmaa El Hannani, Hassan Ouahmane, Thomas Hain
2018 J jnl
Lightly supervised alignment of subtitles on multi-genre broadcasts.
Multim. Tools Appl.
Oscar Saz, Salil Deena, Mortaza Doulaty, Madina Hasan, Bilal Khaliq, Rosanna Milner, Raymond W. M. Ng, Julia Olcoz, Thomas Hain
2017 C conf
Exploring the use of acoustic embeddings in neural machine translation.
ASRU
Salil Deena, Raymond W. M. Ng, Pranava Swaroop Madhyastha, Lucia Specia, Thomas Hain
2017 A conf
Semi-Supervised Adaptation of RNNLMs by Fine-Tuning with Domain-Specific Auxiliary Features.
INTERSPEECH
Salil Deena, Raymond W. M. Ng, Pranava Swaroop Madhyastha, Lucia Specia, Thomas Hain
2016 A conf
Combining Feature and Model-Based Adaptation of RNNLMs for Multi-Genre Broadcast Speech Recognition.
INTERSPEECH
Salil Deena, Madina Hasan, Mortaza Doulaty, Oscar Saz, Thomas Hain
2016 A conf
webASR 2 - Improved Cloud Based Speech Technology.
INTERSPEECH
Thomas Hain, Jeremy Christian, Oscar Saz, Salil Deena, Madina Hasan, Raymond W. M. Ng, Rosanna Milner, Mortaza Doulaty, Yulan Liu
2015 J jnl
The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media.
CoRR
Oscar Saz, Mortaza Doulaty, Salil Deena, Rosanna Milner, Raymond W. M. Ng, Madina Hasan, Yulan Liu, Thomas Hain
2015 C conf
The 2015 sheffield system for longitudinal diarisation of broadcast media.
ASRU
Rosanna Milner, Oscar Saz, Salil Deena, Mortaza Doulaty, Raymond W. M. Ng, Thomas Hain
2015 C conf
The 2015 sheffield system for transcription of Multi-Genre Broadcast media.
ASRU
Oscar Saz, Mortaza Doulaty, Salil Deena, Rosanna Milner, Raymond W. M. Ng, Madina Hasan, Yulan Liu, Thomas Hain
2013 J jnl
Visual Speech Synthesis Using a Variable-Order Switching Shared Gaussian Process Dynamical Model.
IEEE Trans. Multim.
Salil Deena, Shaobo Hou, Aphrodite Galata
2010 — conf
Visual speech synthesis by modelling coarticulation dynamics using a non-parametric switching state-space model.
ICMI-MLMI
Salil Deena, Shaobo Hou, Aphrodite Galata
2009 — conf
Speech-Driven Facial Animation Using a Shared Gaussian Process Latent Variable Model.
ISVC (1)
Salil Deena, Aphrodite Galata