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. @article{DBLP:journals/taslp/DeenaHDSH19,
title = {Recurrent Neural Network Language Model Adaptation for Multi-Genre
Broadcast Speech Recognition and Alignment},
author = {Salil Deena and Madina Hasan and Mortaza Doulaty and Oscar Saz and Thomas Hain},
url = {https://doi.org/10.1109/TASLP.2018.2888814},
doi = {10.1109/TASLP.2018.2888814},
year = {2019},
date = {2019-01-01},
journal = {IEEE ACM Trans. Audio Speech Lang. Process.},
volume = {27},
number = {3},
pages = {572--582},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
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. @article{DBLP:journals/mta/SazDDHKMNOH18,
title = {Lightly supervised alignment of subtitles on multi-genre broadcasts},
author = {Oscar Saz and Salil Deena and Mortaza Doulaty and Madina Hasan and Bilal Khaliq and Rosanna Milner and Raymond W. M. Ng and Julia Olcoz and Thomas Hain},
url = {https://doi.org/10.1007/s11042-018-6050-1},
doi = {10.1007/s11042-018-6050-1},
year = {2018},
date = {2018-01-01},
journal = {Multim. Tools Appl.},
volume = {77},
number = {23},
pages = {30533--30550},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
2017
|
Oscar Saz; Thomas Hain: Acoustic adaptation to dynamic background conditions with asynchronous
transformations. In: Comput. Speech Lang., vol. 41, pp. 180–194, 2017. @article{DBLP:journals/csl/SazH17,
title = {Acoustic adaptation to dynamic background conditions with asynchronous
transformations},
author = {Oscar Saz and Thomas Hain},
url = {https://doi.org/10.1016/j.csl.2016.06.008},
doi = {10.1016/j.csl.2016.06.008},
year = {2017},
date = {2017-01-01},
journal = {Comput. Speech Lang.},
volume = {41},
pages = {180--194},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Chenhao Wu; Raymond W. M. Ng; Oscar Saz; Thomas Hain: Analysing acoustic model changes for active learning in automatic speech recognition. In: International Conference on Systems, Signals and Image Processing,
IWSSIP 2017, Poznań, Poland, May 22-24, 2017, pp. 1–5, IEEE, 2017. @inproceedings{DBLP:conf/iwssip/WuNSH17,
title = {Analysing acoustic model changes for active learning in automatic speech recognition},
author = {Chenhao Wu and Raymond W. M. Ng and Oscar Saz and Thomas Hain},
url = {https://doi.org/10.1109/IWSSIP.2017.7965609},
doi = {10.1109/IWSSIP.2017.7965609},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
booktitle = {International Conference on Systems, Signals and Image Processing,
IWSSIP 2017, Poznań, Poland, May 22-24, 2017},
pages = {1--5},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Erfan Loweimi; Jon Barker; Oscar Saz; Thomas Hain: Robust Source-Filter Separation of Speech Signal in the Phase Domain. In: Lacerda, Francisco (Ed.): Interspeech 2017, 18th Annual Conference of the International Speech
Communication Association, Stockholm, Sweden, August 20-24, 2017, pp. 414–418, ISCA, 2017. @inproceedings{DBLP:conf/interspeech/LoweimiBSH17,
title = {Robust Source-Filter Separation of Speech Signal in the Phase Domain},
author = {Erfan Loweimi and Jon Barker and Oscar Saz and Thomas Hain},
editor = {Francisco Lacerda},
url = {http://www.isca-speech.org/archive/Interspeech_2017/abstracts/0210.html},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech
Communication Association, Stockholm, Sweden, August 20-24, 2017},
pages = {414--418},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
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. @inproceedings{DBLP:conf/interspeech/HainCSDHNMDL16,
title = {webASR 2 - Improved Cloud Based Speech Technology},
author = {Thomas Hain and Jeremy Christian and Oscar Saz and Salil Deena and Madina Hasan and Raymond W. M. Ng and Rosanna Milner and Mortaza Doulaty and Yulan Liu},
editor = {Nelson Morgan},
url = {https://doi.org/10.21437/Interspeech.2016-700},
doi = {10.21437/Interspeech.2016-700},
year = {2016},
date = {2016-01-01},
booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016},
pages = {1613--1617},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Julia Olcoz; Oscar Saz; Thomas Hain: Error Correction in Lightly Supervised Alignment of Broadcast Subtitles. In: Morgan, Nelson (Ed.): Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016, pp. 2110–2114, ISCA, 2016. @inproceedings{DBLP:conf/interspeech/OlcozSH16,
title = {Error Correction in Lightly Supervised Alignment of Broadcast Subtitles},
author = {Julia Olcoz and Oscar Saz and Thomas Hain},
editor = {Nelson Morgan},
url = {https://doi.org/10.21437/Interspeech.2016-56},
doi = {10.21437/Interspeech.2016-56},
year = {2016},
date = {2016-01-01},
booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016},
pages = {2110--2114},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Mortaza Doulaty; Oscar Saz; Raymond W. M. Ng; Thomas Hain: Automatic Genre and Show Identification of Broadcast Media. In: Morgan, Nelson (Ed.): Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016, pp. 2115–2119, ISCA, 2016. @inproceedings{DBLP:conf/interspeech/DoulatySNH16,
title = {Automatic Genre and Show Identification of Broadcast Media},
author = {Mortaza Doulaty and Oscar Saz and Raymond W. M. Ng and Thomas Hain},
editor = {Nelson Morgan},
url = {https://doi.org/10.21437/Interspeech.2016-472},
doi = {10.21437/Interspeech.2016-472},
year = {2016},
date = {2016-01-01},
booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016},
pages = {2115--2119},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
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. @inproceedings{DBLP:conf/interspeech/DeenaHDSH16,
title = {Combining Feature and Model-Based Adaptation of RNNLMs for Multi-Genre
Broadcast Speech Recognition},
author = {Salil Deena and Madina Hasan and Mortaza Doulaty and Oscar Saz and Thomas Hain},
editor = {Nelson Morgan},
url = {https://doi.org/10.21437/Interspeech.2016-480},
doi = {10.21437/Interspeech.2016-480},
year = {2016},
date = {2016-01-01},
booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016},
pages = {2343--2347},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Raymond W. M. Ng; Mauro Nicolao; Oscar Saz; Madina Hasan; Bhusan Chettri; Mortaza Doulaty; Tan Lee; Thomas Hain: The Sheffield language recognition system in NIST LRE 2015. In: Rodríguez-Fuentes, Luis Javier; Lleida, Eduardo (Ed.): Odyssey 2016: The Speaker and Language Recognition Workshop, Bilbao,
Spain, June 21-24, 2016, pp. 181–187, ISCA, 2016. @inproceedings{DBLP:conf/odyssey/NgNSHCDLH16,
title = {The Sheffield language recognition system in NIST LRE 2015},
author = {Raymond W. M. Ng and Mauro Nicolao and Oscar Saz and Madina Hasan and Bhusan Chettri and Mortaza Doulaty and Tan Lee and Thomas Hain},
editor = {Luis Javier Rodríguez-Fuentes and Eduardo Lleida},
url = {https://doi.org/10.21437/Odyssey.2016-26},
doi = {10.21437/Odyssey.2016-26},
year = {2016},
date = {2016-01-01},
booktitle = {Odyssey 2016: The Speaker and Language Recognition Workshop, Bilbao,
Spain, June 21-24, 2016},
pages = {181--187},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2015
|
Mortaza Doulaty; Oscar Saz; Raymond W. M. Ng; Thomas Hain: Latent Dirichlet Allocation based organisation of broadcast media
archives for deep neural network adaptation. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding,
ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015, pp. 130–136, IEEE, 2015. @inproceedings{DBLP:conf/asru/DoulatySNH15,
title = {Latent Dirichlet Allocation based organisation of broadcast media
archives for deep neural network adaptation},
author = {Mortaza Doulaty and Oscar Saz and Raymond W. M. Ng and Thomas Hain},
url = {https://doi.org/10.1109/ASRU.2015.7404785},
doi = {10.1109/ASRU.2015.7404785},
year = {2015},
date = {2015-01-01},
booktitle = {2015 IEEE Workshop on Automatic Speech Recognition and Understanding,
ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015},
pages = {130--136},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
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. @inproceedings{DBLP:conf/asru/SazDDMNHLH15,
title = {The 2015 sheffield system for transcription of Multi-Genre Broadcast
media},
author = {Oscar Saz and Mortaza Doulaty and Salil Deena and Rosanna Milner and Raymond W. M. Ng and Madina Hasan and Yulan Liu and Thomas Hain},
url = {https://doi.org/10.1109/ASRU.2015.7404854},
doi = {10.1109/ASRU.2015.7404854},
year = {2015},
date = {2015-01-01},
booktitle = {2015 IEEE Workshop on Automatic Speech Recognition and Understanding,
ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015},
pages = {624--631},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
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. @inproceedings{DBLP:conf/asru/MilnerSDDNH15,
title = {The 2015 sheffield system for longitudinal diarisation of broadcast
media},
author = {Rosanna Milner and Oscar Saz and Salil Deena and Mortaza Doulaty and Raymond W. M. Ng and Thomas Hain},
url = {https://doi.org/10.1109/ASRU.2015.7404855},
doi = {10.1109/ASRU.2015.7404855},
year = {2015},
date = {2015-01-01},
booktitle = {2015 IEEE Workshop on Automatic Speech Recognition and Understanding,
ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015},
pages = {632--638},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Peter Bell; Mark J. F. Gales; Thomas Hain; Jonathan Kilgour; Pierre Lanchantin; Xunying Liu; Andrew McParland; Steve Renals; Oscar Saz; Mirjam Wester; Philip C. Woodland: The MGB challenge: Evaluating multi-genre broadcast media recognition. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding,
ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015, pp. 687–693, IEEE, 2015. @inproceedings{DBLP:conf/asru/BellGHKLLMRSWW15,
title = {The MGB challenge: Evaluating multi-genre broadcast media recognition},
author = {Peter Bell and Mark J. F. Gales and Thomas Hain and Jonathan Kilgour and Pierre Lanchantin and Xunying Liu and Andrew McParland and Steve Renals and Oscar Saz and Mirjam Wester and Philip C. Woodland},
url = {https://doi.org/10.1109/ASRU.2015.7404863},
doi = {10.1109/ASRU.2015.7404863},
year = {2015},
date = {2015-01-01},
booktitle = {2015 IEEE Workshop on Automatic Speech Recognition and Understanding,
ASRU 2015, Scottsdale, AZ, USA, December 13-17, 2015},
pages = {687--693},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Mortaza Doulaty; Oscar Saz; Thomas Hain: Data-selective transfer learning for multi-domain speech recognition. In: INTERSPEECH 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015, pp. 2897–2901, ISCA, 2015. @inproceedings{DBLP:conf/interspeech/DoulatySH15,
title = {Data-selective transfer learning for multi-domain speech recognition},
author = {Mortaza Doulaty and Oscar Saz and Thomas Hain},
url = {http://www.isca-speech.org/archive/interspeech_2015/i15_2897.html},
year = {2015},
date = {2015-01-01},
booktitle = {INTERSPEECH 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015},
pages = {2897--2901},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Mortaza Doulaty; Oscar Saz; Thomas Hain: Unsupervised domain discovery using latent dirichlet allocation for
acoustic modelling in speech recognition. In: INTERSPEECH 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015, pp. 3640–3644, ISCA, 2015. @inproceedings{DBLP:conf/interspeech/DoulatySH15a,
title = {Unsupervised domain discovery using latent dirichlet allocation for
acoustic modelling in speech recognition},
author = {Mortaza Doulaty and Oscar Saz and Thomas Hain},
url = {http://www.isca-speech.org/archive/interspeech_2015/i15_3640.html},
year = {2015},
date = {2015-01-01},
booktitle = {INTERSPEECH 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015},
pages = {3640--3644},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2014
|
Oscar Saz; Thomas Hain: Using contextual information in joint factor eigenspace MLLR for
speech recognition in diverse scenarios. In: IEEE International Conference on Acoustics, Speech and Signal Processing,
ICASSP 2014, Florence, Italy, May 4-9, 2014, pp. 6314–6318, IEEE, 2014. @inproceedings{DBLP:conf/icassp/SazH14,
title = {Using contextual information in joint factor eigenspace MLLR for
speech recognition in diverse scenarios},
author = {Oscar Saz and Thomas Hain},
url = {https://doi.org/10.1109/ICASSP.2014.6854819},
doi = {10.1109/ICASSP.2014.6854819},
year = {2014},
date = {2014-01-01},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing,
ICASSP 2014, Florence, Italy, May 4-9, 2014},
pages = {6314--6318},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Oscar Saz; Mortaza Doulaty; Thomas Hain: Background-tracking acoustic features for genre identification of
broadcast shows. In: 2014 IEEE Spoken Language Technology Workshop, SLT 2014, South
Lake Tahoe, NV, USA, December 7-10, 2014, pp. 118–123, IEEE, 2014. @inproceedings{DBLP:conf/slt/SazDH14,
title = {Background-tracking acoustic features for genre identification of
broadcast shows},
author = {Oscar Saz and Mortaza Doulaty and Thomas Hain},
url = {https://doi.org/10.1109/SLT.2014.7078560},
doi = {10.1109/SLT.2014.7078560},
year = {2014},
date = {2014-01-01},
booktitle = {2014 IEEE Spoken Language Technology Workshop, SLT 2014, South
Lake Tahoe, NV, USA, December 7-10, 2014},
pages = {118--123},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Raymond W. M. Ng; Mortaza Doulaty; Rama Doddipatla; Wilker Aziz; Kashif Shah; Oscar Saz; Madina Hasan; Ghada AlHarbi; Lucia Specia; Thomas Hain: The USFD SLT system for IWSLT 2014. In: Federico, Marcello; Stüker, Sebastian; Yvon, François (Ed.): Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign@IWSLT 2014, Lake Tahoe, CA, USA,
December 4-5, 2014, 2014. @inproceedings{DBLP:conf/iwslt/NgDDASSHASH14,
title = {The USFD SLT system for IWSLT 2014},
author = {Raymond W. M. Ng and Mortaza Doulaty and Rama Doddipatla and Wilker Aziz and Kashif Shah and Oscar Saz and Madina Hasan and Ghada AlHarbi and Lucia Specia and Thomas Hain},
editor = {Marcello Federico and Sebastian Stüker and François Yvon},
url = {https://aclanthology.org/2014.iwslt-evaluation.11},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
booktitle = {Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign@IWSLT 2014, Lake Tahoe, CA, USA,
December 4-5, 2014},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2013
|
Pierre Lanchantin; Peter Bell; Mark J. F. Gales; Thomas Hain; Xunying Liu; Yanhua Long; Jennifer Quinnell; Steve Renals; Oscar Saz; Matthew Stephen Seigel; Pawel Swietojanski; Philip C. Woodland: Automatic Transcription of Multi-genre Media Archives. In: Gravier, Guillaume; Béchet, Frédéric (Ed.): Proceedings of the First Workshop on Speech, Language and Audio in
Multimedia, Marseille, France, August 22-23, 2013, pp. 26–31, CEUR-WS.org, 2013. @inproceedings{DBLP:conf/interspeech/Lanchantin13,
title = {Automatic Transcription of Multi-genre Media Archives},
author = {Pierre Lanchantin and Peter Bell and Mark J. F. Gales and Thomas Hain and Xunying Liu and Yanhua Long and Jennifer Quinnell and Steve Renals and Oscar Saz and Matthew Stephen Seigel and Pawel Swietojanski and Philip C. Woodland},
editor = {Guillaume Gravier and Frédéric Béchet},
url = {http://ceur-ws.org/Vol-1012/papers/paper-05.pdf},
year = {2013},
date = {2013-01-01},
booktitle = {Proceedings of the First Workshop on Speech, Language and Audio in
Multimedia, Marseille, France, August 22-23, 2013},
volume = {1012},
pages = {26--31},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Oscar Saz; Thomas Hain: Asynchronous factorisation of speaker and background with feature
transforms in speech recognition. In: Bimbot, Frédéric; Cerisara, Christophe; Fougeron, Cécile; Gravier, Guillaume; Lamel, Lori; Pellegrino, François; Perrier, Pascal (Ed.): INTERSPEECH 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013, pp. 1238–1242, ISCA, 2013. @inproceedings{DBLP:conf/interspeech/SazH13,
title = {Asynchronous factorisation of speaker and background with feature
transforms in speech recognition},
author = {Oscar Saz and Thomas Hain},
editor = {Frédéric Bimbot and Christophe Cerisara and Cécile Fougeron and Guillaume Gravier and Lori Lamel and François Pellegrino and Pascal Perrier},
url = {http://www.isca-speech.org/archive/interspeech_2013/i13_1238.html},
year = {2013},
date = {2013-01-01},
booktitle = {INTERSPEECH 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {1238--1242},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
