2015
|
Erfan Loweimi; Mortaza Doulaty; Jon Barker; Thomas Hain: Long-Term Statistical Feature Extraction from Speech Signal and Its
Application in Emotion Recognition. In: Dediu, Adrian-Horia; Martín-Vide, Carlos; Vicsi, Klára (Ed.): Statistical Language and Speech Processing - Third International Conference,
SLSP 2015, Budapest, Hungary, November 24-26, 2015, Proceedings, pp. 173–184, Springer, 2015. @inproceedings{DBLP:conf/slsp/LoweimiDBH15,
title = {Long-Term Statistical Feature Extraction from Speech Signal and Its
Application in Emotion Recognition},
author = {Erfan Loweimi and Mortaza Doulaty and Jon Barker and Thomas Hain},
editor = {Adrian-Horia Dediu and Carlos Martín-Vide and Klára Vicsi},
url = {https://doi.org/10.1007/978-3-319-25789-1_17},
doi = {10.1007/978-3-319-25789-1_17},
year = {2015},
date = {2015-01-01},
booktitle = {Statistical Language and Speech Processing - Third International Conference,
SLSP 2015, Budapest, Hungary, November 24-26, 2015, Proceedings},
volume = {9449},
pages = {173--184},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Madina Hasan; Rama Doddipatla; Thomas Hain: Noise-matched training of CRF based sentence end detection models. In: INTERSPEECH 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015, pp. 349–353, ISCA, 2015. @inproceedings{DBLP:conf/interspeech/HasanDH15,
title = {Noise-matched training of CRF based sentence end detection models},
author = {Madina Hasan and Rama Doddipatla and Thomas Hain},
url = {http://www.isca-speech.org/archive/interspeech_2015/i15_0349.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 = {349--353},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Raymond W. M. Ng; Kashif Shah; Wilker Aziz; Lucia Specia; Thomas Hain: Quality estimation for asr k-best list rescoring in spoken language
translation. In: 2015 IEEE International Conference on Acoustics, Speech and Signal
Processing, ICASSP 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015, pp. 5226–5230, IEEE, 2015. @inproceedings{DBLP:conf/icassp/NgSASH15,
title = {Quality estimation for asr k-best list rescoring in spoken language
translation},
author = {Raymond W. M. Ng and Kashif Shah and Wilker Aziz and Lucia Specia and Thomas Hain},
url = {https://doi.org/10.1109/ICASSP.2015.7178968},
doi = {10.1109/ICASSP.2015.7178968},
year = {2015},
date = {2015-01-01},
booktitle = {2015 IEEE International Conference on Acoustics, Speech and Signal
Processing, ICASSP 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {5226--5230},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Erfan Loweimi; Jon Barker; Thomas Hain: Source-filter separation of speech signal in the phase domain. In: INTERSPEECH 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015, pp. 598–602, ISCA, 2015. @inproceedings{DBLP:conf/interspeech/LoweimiBH15,
title = {Source-filter separation of speech signal in the phase domain},
author = {Erfan Loweimi and Jon Barker and Thomas Hain},
url = {http://www.isca-speech.org/archive/interspeech_2015/i15_0598.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 = {598--602},
publisher = {ISCA},
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}
}
|
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}
}
|
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: 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}
}
|
Ghada AlHarbi; Thomas Hain: Using Topic Segmentation Models for the Automatic Organisation of
MOOCs resources. In: Santos, Olga C.; Boticario, Jesus; Romero, Cristóbal; Pechenizkiy, Mykola; Merceron, Agathe; Mitros, Piotr; Luna, José María; Mihaescu, Marian Cristian; Moreno, Pablo; Hershkovitz, Arnon; Ventura, Sebastián; Desmarais, Michel C. (Ed.): Proceedings of the 8th International Conference on Educational Data
Mining, EDM 2015, Madrid, Spain, June 26-29, 2015, pp. 524–527, International Educational Data Mining Society (IEDMS), 2015. @inproceedings{DBLP:conf/edm/AlHarbiH15,
title = {Using Topic Segmentation Models for the Automatic Organisation of
MOOCs resources},
author = {Ghada AlHarbi and Thomas Hain},
editor = {Olga C. Santos and Jesus Boticario and Cristóbal Romero and Mykola Pechenizkiy and Agathe Merceron and Piotr Mitros and José María Luna and Marian Cristian Mihaescu and Pablo Moreno and Arnon Hershkovitz and Sebastián Ventura and Michel C. Desmarais},
url = {http://www.educationaldatamining.org/EDM2015/proceedings/short524-527.pdf},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of the 8th International Conference on Educational Data
Mining, EDM 2015, Madrid, Spain, June 26-29, 2015},
pages = {524--527},
publisher = {International Educational Data Mining Society (IEDMS)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2014
|
Pengyuan Zhang; Yulan Liu; Thomas Hain: Semi-Supervised DNN Training in Meeting Recognition. In: 2014 IEEE Spoken Language Technology Workshop (SLT 2014), South Lake Tahoe, USA, 2014. @inproceedings{zhang2014,
title = {Semi-Supervised DNN Training in Meeting Recognition},
author = {Pengyuan Zhang and Yulan Liu and Thomas Hain},
doi = {10.1109/SLT.2014.7078564},
year = {2014},
date = {2014-12-01},
booktitle = {2014 IEEE Spoken Language Technology Workshop (SLT 2014)},
address = {South Lake Tahoe, USA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Yulan Liu; Pengyuan Zhang; Thomas Hain: Using neural network front-ends on far field multiple microphones based speech recognition. In: Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on, pp. 5542-5546, 2014. @inproceedings{liu2014,
title = {Using neural network front-ends on far field multiple microphones based speech recognition},
author = {Yulan Liu and Pengyuan Zhang and Thomas Hain},
doi = {10.1109/ICASSP.2014.6854663},
year = {2014},
date = {2014-05-01},
booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on},
pages = {5542-5546},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Inigo Casanueva; Heidi Christensen; Thomas Hain; Phil D. Green: Adaptive speech recognition and dialogue management for users with speech disorders. In: Li, Haizhou; Meng, Helen M.; Ma, Bin; Chng, Engsiong; Xie, Lei (Ed.): INTERSPEECH 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014, pp. 1033–1037, ISCA, 2014. @inproceedings{DBLP:conf/interspeech/CasanuevaCHG14,
title = {Adaptive speech recognition and dialogue management for users with speech disorders},
author = {Inigo Casanueva and Heidi Christensen and Thomas Hain and Phil D. Green},
editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie},
url = {http://www.isca-speech.org/archive/interspeech_2014/i14_1033.html},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
booktitle = {INTERSPEECH 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014},
pages = {1033--1037},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Heidi Christensen; Inigo Casanueva; Stuart P. Cunningham; Phil D. Green; Thomas Hain: Automatic selection of speakers for improved acoustic modelling: recognition of disordered speech with sparse data. In: 2014 IEEE Spoken Language Technology Workshop, SLT 2014, South
Lake Tahoe, NV, USA, December 7-10, 2014, pp. 254–259, IEEE, 2014. @inproceedings{DBLP:conf/slt/ChristensenCCGH14,
title = {Automatic selection of speakers for improved acoustic modelling: recognition of disordered speech with sparse data},
author = {Heidi Christensen and Inigo Casanueva and Stuart P. Cunningham and Phil D. Green and Thomas Hain},
url = {https://doi.org/10.1109/SLT.2014.7078583},
doi = {10.1109/SLT.2014.7078583},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
booktitle = {2014 IEEE Spoken Language Technology Workshop, SLT 2014, South
Lake Tahoe, NV, USA, December 7-10, 2014},
pages = {254--259},
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}
}
|
Erfan Loweimi; Jon Barker; Thomas Hain: Compression of model-based group delay function for robust speech recognition. In: University of Sheffield Engineering Symposium, Sheffield, UK, 2014. @inproceedings{loweimi_uses14,
title = {Compression of model-based group delay function for robust speech recognition},
author = {Erfan Loweimi and Jon Barker and Thomas Hain},
year = {2014},
date = {2014-01-01},
urldate = {2014-01-01},
booktitle = {University of Sheffield Engineering Symposium},
address = {Sheffield, UK},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Charles Fox; Thomas Hain: Extending Limabeam with discrimination and coarse gradients. In: Li, Haizhou; Meng, Helen M.; Ma, Bin; Chng, Engsiong; Xie, Lei (Ed.): INTERSPEECH 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014, pp. 2440–2444, ISCA, 2014. @inproceedings{DBLP:conf/interspeech/FoxH14,
title = {Extending Limabeam with discrimination and coarse gradients},
author = {Charles Fox and Thomas Hain},
editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie},
url = {http://www.isca-speech.org/archive/interspeech_2014/i14_2440.html},
year = {2014},
date = {2014-01-01},
booktitle = {INTERSPEECH 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014},
pages = {2440--2444},
publisher = {ISCA},
crossref = {DBLP:conf/interspeech/2014},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Madina Hasan; Rama Doddipatla; Thomas Hain: Multi-pass sentence-end detection of lecture speech. In: Li, Haizhou; Meng, Helen M.; Ma, Bin; Chng, Engsiong; Xie, Lei (Ed.): INTERSPEECH 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014, pp. 2902–2906, ISCA, 2014. @inproceedings{DBLP:conf/interspeech/HasanDH14,
title = {Multi-pass sentence-end detection of lecture speech},
author = {Madina Hasan and Rama Doddipatla and Thomas Hain},
editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie},
url = {http://www.isca-speech.org/archive/interspeech_2014/i14_2902.html},
year = {2014},
date = {2014-01-01},
booktitle = {INTERSPEECH 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014},
pages = {2902--2906},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Pengyuan Zhang; Yulan Liu; Thomas Hain: Semi-supervised DNN training in meeting recognition. In: 2014 IEEE Spoken Language Technology Workshop, SLT 2014, South
Lake Tahoe, NV, USA, December 7-10, 2014, pp. 141–146, IEEE, 2014. @inproceedings{DBLP:conf/slt/ZhangLH14,
title = {Semi-supervised DNN training in meeting recognition},
author = {Pengyuan Zhang and Yulan Liu and Thomas Hain},
url = {https://doi.org/10.1109/SLT.2014.7078564},
doi = {10.1109/SLT.2014.7078564},
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 = {141--146},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Rama Doddipatla; Madina Hasan; Thomas Hain: Speaker dependent bottleneck layer training for speaker adaptation
in automatic speech recognition. In: Li, Haizhou; Meng, Helen M.; Ma, Bin; Chng, Engsiong; Xie, Lei (Ed.): INTERSPEECH 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014, pp. 2199–2203, ISCA, 2014. @inproceedings{DBLP:conf/interspeech/DoddipatlaHH14,
title = {Speaker dependent bottleneck layer training for speaker adaptation
in automatic speech recognition},
author = {Rama Doddipatla and Madina Hasan and Thomas Hain},
editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie},
url = {http://www.isca-speech.org/archive/interspeech_2014/i14_2199.html},
year = {2014},
date = {2014-01-01},
booktitle = {INTERSPEECH 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014},
pages = {2199--2203},
publisher = {ISCA},
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}
}
|
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}
}
|
Yulan Liu; Pengyuan Zhang; Thomas Hain: Using neural network front-ends on far field multiple microphones
based speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing,
ICASSP 2014, Florence, Italy, May 4-9, 2014, pp. 5542–5546, IEEE, 2014. @inproceedings{DBLP:conf/icassp/LiuZH14,
title = {Using neural network front-ends on far field multiple microphones
based speech recognition},
author = {Yulan Liu and Pengyuan Zhang and Thomas Hain},
url = {https://doi.org/10.1109/ICASSP.2014.6854663},
doi = {10.1109/ICASSP.2014.6854663},
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 = {5542--5546},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2013
|
Mauro Nicolao; Fabio Tesser; Roger K. Moore: A phonetic-contrast motivated adaptation to control the degree-of-articulation on Italian HMM-based synthetic voices. In: 8th ISCA Workshop on Speech Synthesis, pp. 127–132, Barcelona, Spain, 2013. @inproceedings{nicolao_ssw8,
title = {A phonetic-contrast motivated adaptation to control the degree-of-articulation on Italian HMM-based synthetic voices},
author = {Mauro Nicolao and Fabio Tesser and Roger K. Moore},
year = {2013},
date = {2013-08-01},
urldate = {2013-08-01},
booktitle = {8th ISCA Workshop on Speech Synthesis},
pages = {127--132},
address = {Barcelona, Spain},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Erfan Loweimi; Seyed Mohammad Ahadi; Thomas Drugman: A new phase-based feature representation for robust speech recognition. In: IEEE International conference on Acoustics, Speech and Signal Processing, Vancouver, Canada, 2013. @inproceedings{loweimi_icassp13,
title = {A new phase-based feature representation for robust speech recognition},
author = {Erfan Loweimi and Seyed Mohammad Ahadi and Thomas Drugman},
year = {2013},
date = {2013-01-01},
booktitle = {IEEE International conference on Acoustics, Speech and Signal Processing},
address = {Vancouver, Canada},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Raymond W. M. Ng; Thomas Hain; Trevor Cohn: Adaptation of lecture speech recognition system with machine translation
output. In: IEEE International Conference on Acoustics, Speech and Signal Processing,
ICASSP 2013, Vancouver, BC, Canada, May 26-31, 2013, pp. 8401–8405, IEEE, 2013. @inproceedings{DBLP:conf/icassp/NgHC13,
title = {Adaptation of lecture speech recognition system with machine translation
output},
author = {Raymond W. M. Ng and Thomas Hain and Trevor Cohn},
url = {https://doi.org/10.1109/ICASSP.2013.6639304},
doi = {10.1109/ICASSP.2013.6639304},
year = {2013},
date = {2013-01-01},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing,
ICASSP 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {8401--8405},
publisher = {IEEE},
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}
}
|
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}
}
|
Heidi Christensen; M. B. Aniol; Peter Bell; Phil D. Green; Thomas Hain; Simon King; Pawel Swietojanski: Combining in-domain and out-of-domain speech data for automatic recognition
of disordered speech. 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. 3642–3645, ISCA, 2013. @inproceedings{DBLP:conf/interspeech/ChristensenABGHKS13,
title = {Combining in-domain and out-of-domain speech data for automatic recognition
of disordered speech},
author = {Heidi Christensen and M. B. Aniol and Peter Bell and Phil D. Green and Thomas Hain and Simon King and Pawel Swietojanski},
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_3642.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 = {3642--3645},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sarah Al-Shareef : Conversational Arabic Automatic Speech Recognition: Literature Review. The University of Sheffield 2013. @techreport{Alshareef13TR,
title = {Conversational Arabic Automatic Speech Recognition: Literature Review},
author = {Sarah Al-Shareef },
year = {2013},
date = {2013-01-01},
urldate = {2013-01-01},
institution = {The University of Sheffield},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
|
D. M González; Phil D. Green; Heidi Christensen: Dysarthria Intelligibility Assessment in a Factor Analysis Total Variability Space. Interspeech’13, 2013. @conference{Gonzalez2013,
title = {Dysarthria Intelligibility Assessment in a Factor Analysis Total Variability Space},
author = {D. M González and Phil D. Green and Heidi Christensen},
url = {http://staffwww.dcs.shef.ac.uk/people/H.Christensen/pubs/christensen_is13_3.pdf},
year = {2013},
date = {2013-01-01},
urldate = {2013-01-01},
booktitle = {Interspeech’13},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
Heidi Christensen; Iñigo Casanueva; Stuart P. Cunningham; Phil D. Green; Thomas Hain: homeService: Voice-enabled assistive technology in the home using cloud-based automatic speech recognition. In: Alexandersson, Jan; Ljunglöf, Peter; McCoy, Kathleen F.; Portet, François; Roark, Brian; Rudzicz, Frank; Vacher, Michel (Ed.): Proceedings of the Fourth Workshop on Speech and Language Processing
for Assistive Technologies, SLPAT 2013, Grenoble, France, August
21-22, 2013, pp. 29–34, Association for Computational Linguistics, 2013. @inproceedings{DBLP:conf/slpat/ChristensenCCGH13,
title = {homeService: Voice-enabled assistive technology in the home using cloud-based automatic speech recognition},
author = {Heidi Christensen and Iñigo Casanueva and Stuart P. Cunningham and Phil D. Green and Thomas Hain},
editor = {Jan Alexandersson and Peter Ljunglöf and Kathleen F. McCoy and François Portet and Brian Roark and Frank Rudzicz and Michel Vacher},
url = {https://aclanthology.org/W13-3906/},
year = {2013},
date = {2013-01-01},
urldate = {2013-01-01},
booktitle = {Proceedings of the Fourth Workshop on Speech and Language Processing
for Assistive Technologies, SLPAT 2013, Grenoble, France, August
21-22, 2013},
pages = {29--34},
publisher = {Association for Computational Linguistics},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Heidi Christensen; Phil D. Green; Thomas Hain: Learning speaker-specific pronunciations of disordered speech. 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. 1159–1163, ISCA, 2013. @inproceedings{DBLP:conf/interspeech/ChristensenGH13,
title = {Learning speaker-specific pronunciations of disordered speech},
author = {Heidi Christensen and Phil D. Green 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_1159.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 = {1159--1163},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Charles Fox; Thomas Hain: Lightly supervised learning from a damaged natural speech corpus. In: IEEE International Conference on Acoustics, Speech and Signal Processing,
ICASSP 2013, Vancouver, BC, Canada, May 26-31, 2013, pp. 8086–8090, IEEE, 2013. @inproceedings{DBLP:conf/icassp/FoxH13,
title = {Lightly supervised learning from a damaged natural speech corpus},
author = {Charles Fox and Thomas Hain},
url = {https://doi.org/10.1109/ICASSP.2013.6639240},
doi = {10.1109/ICASSP.2013.6639240},
year = {2013},
date = {2013-01-01},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing,
ICASSP 2013, Vancouver, BC, Canada, May 26-31, 2013},
pages = {8086--8090},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Erfan Loweimi; Seyed Mohammad Ahadi; Thomas Drugman; Samira Loveymi: On the importance of pre-emphasis and window shape in phase-based speech recognition. In: Lecture Notes in Computer Science, Advances in Non-Linear Speech Processing (NOLISP), Mons, Belgium, 2013. @inproceedings{loweimi_nolisp13,
title = {On the importance of pre-emphasis and window shape in phase-based speech recognition},
author = {Erfan Loweimi and Seyed Mohammad Ahadi and Thomas Drugman and Samira Loveymi},
year = {2013},
date = {2013-01-01},
booktitle = {Lecture Notes in Computer Science, Advances in Non-Linear Speech Processing (NOLISP)},
address = {Mons, Belgium},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Charles Fox; Yulan Liu; Erich Zwyssig; Thomas Hain: The Sheffield Wargames Corpus. In: Proc. Interspeech 2013, ISCA, 2013. @inbook{fox2013,
title = {The Sheffield Wargames Corpus},
author = {Charles Fox and Yulan Liu and Erich Zwyssig and Thomas Hain},
year = {2013},
date = {2013-01-01},
urldate = {2013-01-01},
booktitle = {Proc. Interspeech 2013},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
|
Charles Fox; Yulan Liu; Erich Zwyssig; Thomas Hain: The sheffield wargames corpus. 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. 1116–1120, ISCA, 2013. @inproceedings{DBLP:conf/interspeech/FoxLZH13,
title = {The sheffield wargames corpus},
author = {Charles Fox and Yulan Liu and Erich Zwyssig 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_1116.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 = {1116--1120},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2012
|
Heidi Christensen; Stuart P. Cunningham; Charles Fox; Phil D. Green; Thomas Hain: A comparative study of adaptive, automatic recognition of disordered speech. Proc Interspeech 2012, Portland, Oregon, US, 2012. @conference{christensen_is12,
title = {A comparative study of adaptive, automatic recognition of disordered speech},
author = {Heidi Christensen and Stuart P. Cunningham and Charles Fox and Phil D. Green and Thomas Hain},
url = {http://staffwww.dcs.shef.ac.uk/people/H.Christensen/pubs/christensen_is12.pdf},
year = {2012},
date = {2012-09-01},
urldate = {2012-09-01},
booktitle = {Proc Interspeech 2012},
address = {Portland, Oregon, US},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
Mauro Nicolao; Javier Latorre; Roger K. Moore: C2H: A Computational Model of H&H-based Phonetic Contrast in Synthetic Speech. In: Proceedings of 13th Annual Conference of the International Speech Communication Association, INTERSPEECH 2012, Portland, OR, 2012. @inproceedings{nicolao_is12,
title = {C2H: A Computational Model of H&H-based Phonetic Contrast in Synthetic Speech},
author = {Mauro Nicolao and Javier Latorre and Roger K. Moore},
year = {2012},
date = {2012-09-01},
urldate = {2012-09-01},
booktitle = {Proceedings of 13th Annual Conference of the International Speech Communication Association, INTERSPEECH 2012},
address = {Portland, OR},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Mauro Nicolao; Roger K. Moore: Establishing some principles of human speech production through two-dimensional computational models. In: SAPA-SCALE workshop 2012, Portland, OR, 2012. @inproceedings{nicolao_sapa12,
title = {Establishing some principles of human speech production through two-dimensional computational models},
author = {Mauro Nicolao and Roger K. Moore},
year = {2012},
date = {2012-08-01},
urldate = {2012-08-01},
booktitle = {SAPA-SCALE workshop 2012},
address = {Portland, OR},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sarah Al-Shareef; Thomas Hain: Conditional Random Fields Based Diacritisation of Colloquial Arabic. In: Saudi International Conference, 2012. @inproceedings{Alshareef12SIC,
title = {Conditional Random Fields Based Diacritisation of Colloquial Arabic},
author = {Sarah Al-Shareef and Thomas Hain},
year = {2012},
date = {2012-01-01},
urldate = {2012-01-01},
booktitle = {Saudi International Conference},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Matthew Gibson; Thomas Hain: Correctness-Adjusted Unsupervised Discriminative Acoustic Model Adaptation. In: IEEE Trans. Speech Audio Process., vol. 20, no. 10, pp. 2648–2656, 2012. @article{DBLP:journals/taslp/GibsonH12,
title = {Correctness-Adjusted Unsupervised Discriminative Acoustic Model Adaptation},
author = {Matthew Gibson and Thomas Hain},
url = {https://doi.org/10.1109/TASL.2012.2209420},
doi = {10.1109/TASL.2012.2209420},
year = {2012},
date = {2012-01-01},
journal = {IEEE Trans. Speech Audio Process.},
volume = {20},
number = {10},
pages = {2648--2656},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Sarah Al-Shareef; Thomas Hain: CRF-based Diacritisation of Colloquial Arabic for Automatic Speech Recognition. In: INTERSPEECH, 2012. @inproceedings{Alshareef12IS,
title = {CRF-based Diacritisation of Colloquial Arabic for Automatic Speech Recognition},
author = {Sarah Al-Shareef and Thomas Hain},
year = {2012},
date = {2012-01-01},
urldate = {2012-01-01},
booktitle = {INTERSPEECH},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Heidi Christensen; Siddharth Sehgal; Peter O’Neill; Zoe Clarke; Simon Judge; Stuart P. Cunningham; Mark S. Hawley: SPECS - an embedded platform, speech-driven environmental control system evaluated in a virtuous circle framework. Proc. Workshop on Innovation and Applications in Speech Technology, 2012. @conference{Christensen_iast2012,
title = {SPECS - an embedded platform, speech-driven environmental control system evaluated in a virtuous circle framework},
author = {Heidi Christensen and Siddharth Sehgal and Peter O’Neill and Zoe Clarke and Simon Judge and Stuart P. Cunningham and Mark S. Hawley},
url = {http://www.dcs.shef.ac.uk/~heidi/pubs/iast-abstract.pdf},
year = {2012},
date = {2012-01-01},
urldate = {2012-01-01},
booktitle = {Proc. Workshop on Innovation and Applications in Speech Technology},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
Charles Fox; Heidi Christensen; Thomas Hain: Studio report: Linux audio for multi-speaker natural speech technology.. Proc. Linux Audio Conference, 2012. @conference{FOX-LAC2012,
title = {Studio report: Linux audio for multi-speaker natural speech technology.},
author = {Charles Fox and Heidi Christensen and Thomas Hain},
url = {http://staffwww.dcs.shef.ac.uk/people/C.Fox/fox_lac2012.pdf},
year = {2012},
date = {2012-01-01},
urldate = {2012-01-01},
booktitle = {Proc. Linux Audio Conference},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
Thomas Hain; Lukás Burget; John Dines; Philip N. Garner; Frantisek Grézl; Asmaa El Hannani; Marijn Huijbregts; Martin Karafiát; Mike Lincoln; Vincent Wan: Transcribing Meetings With the AMIDA Systems. In: IEEE Trans. Speech Audio Process., vol. 20, no. 2, pp. 486–498, 2012. @article{DBLP:journals/taslp/HainBDGGHHKLW12,
title = {Transcribing Meetings With the AMIDA Systems},
author = {Thomas Hain and Lukás Burget and John Dines and Philip N. Garner and Frantisek Grézl and Asmaa El Hannani and Marijn Huijbregts and Martin Karafiát and Mike Lincoln and Vincent Wan},
url = {https://doi.org/10.1109/TASL.2011.2163395},
doi = {10.1109/TASL.2011.2163395},
year = {2012},
date = {2012-01-01},
journal = {IEEE Trans. Speech Audio Process.},
volume = {20},
number = {2},
pages = {486--498},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
2011
|
Roger K. Moore; Mauro Nicolao: Reactive Speech Synthesis: Actively Managing Phonetic Contrast Along an H&H Continuum. In: Proceedings of the 17th International Congress of Phonetic Sciences, ICPhS 2011, pp. 1422–1425, Hong Kong, China, 2011. @inproceedings{moore_icphs11,
title = {Reactive Speech Synthesis: Actively Managing Phonetic Contrast Along an H&H Continuum},
author = {Roger K. Moore and Mauro Nicolao},
year = {2011},
date = {2011-08-01},
urldate = {2011-08-01},
booktitle = {Proceedings of the 17th International Congress of Phonetic Sciences, ICPhS 2011},
pages = {1422--1425},
address = {Hong Kong, China},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Erfan Loweimi; Seyed Mohammad Ahadi: A new group delay-based feature for robust speech recognition. In: IEEE International conference on Multimedia and Expo (ICME), Barcelona, Spain, 2011. @inproceedings{loweimi_icme11,
title = {A new group delay-based feature for robust speech recognition},
author = {Erfan Loweimi and Seyed Mohammad Ahadi},
year = {2011},
date = {2011-01-01},
booktitle = {IEEE International conference on Multimedia and Expo (ICME)},
address = {Barcelona, Spain},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Davide Marino; Thomas Hain: An Analysis of Automatic Speech Recognition with Multiple Microphones. In: INTERSPEECH 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011, pp. 1281–1284, ISCA, 2011. @inproceedings{DBLP:conf/interspeech/MarinoH11,
title = {An Analysis of Automatic Speech Recognition with Multiple Microphones},
author = {Davide Marino and Thomas Hain},
url = {http://www.isca-speech.org/archive/interspeech_2011/i11_1281.html},
year = {2011},
date = {2011-01-01},
booktitle = {INTERSPEECH 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {1281--1284},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sarah Al-Shareef; Thomas Hain: An Investigation in Speech Recognition for Colloquial Arabic. In: INTERSPEECH, 2011. @inproceedings{Alshareef11IS,
title = {An Investigation in Speech Recognition for Colloquial Arabic},
author = {Sarah Al-Shareef and Thomas Hain},
year = {2011},
date = {2011-01-01},
urldate = {2011-01-01},
booktitle = {INTERSPEECH},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Roger C. F. Tucker; Dan Fry; Vincent Wan; Stuart N. Wrigley; Thomas Hain: Extending Audio Notetaker to Browse WebASR Transcriptions. In: INTERSPEECH 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011, pp. 3329–3330, ISCA, 2011. @inproceedings{DBLP:conf/interspeech/TuckerFWWH11,
title = {Extending Audio Notetaker to Browse WebASR Transcriptions},
author = {Roger C. F. Tucker and Dan Fry and Vincent Wan and Stuart N. Wrigley and Thomas Hain},
url = {http://www.isca-speech.org/archive/interspeech_2011/i11_3329.html},
year = {2011},
date = {2011-01-01},
booktitle = {INTERSPEECH 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {3329--3330},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|