2014
|
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}
}
|
Stuart N. Wrigley; Thomas Hain: Making an Automatic Speech Recognition Service Freely Available on
the Web. In: INTERSPEECH 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011, pp. 3325–3326, ISCA, 2011. @inproceedings{DBLP:conf/interspeech/WrigleyH11a,
title = {Making an Automatic Speech Recognition Service Freely Available on
the Web},
author = {Stuart N. Wrigley and Thomas Hain},
url = {http://www.isca-speech.org/archive/interspeech_2011/i11_3325.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 = {3325--3326},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Erfan Loweimi; Seyed Mohammad Ahadi; Samira Loveymi: On the importance of phase and magnitude spectra in speech enhancement. In: Iranian conference on Electrical Engineering (ICEE), Tehran, Iran, 2011. @inproceedings{loweimi_icee11,
title = {On the importance of phase and magnitude spectra in speech enhancement},
author = {Erfan Loweimi and Seyed Mohammad Ahadi and Samira Loveymi},
year = {2011},
date = {2011-01-01},
booktitle = {Iranian conference on Electrical Engineering (ICEE)},
address = {Tehran, Iran},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Erfan Loweimi; Seyed Mohammad Ahadi; Hamid Sheikhzadeh: Phase-only speech reconstruction using very short frames. In: Proceedings of the 12th Annual Conference of the International Speech Communication Association (INTERSPEECH), Florence, Italy, 2011. @inproceedings{loweimi_is11,
title = {Phase-only speech reconstruction using very short frames},
author = {Erfan Loweimi and Seyed Mohammad Ahadi and Hamid Sheikhzadeh},
year = {2011},
date = {2011-01-01},
booktitle = {Proceedings of the 12th Annual Conference of the International Speech Communication Association (INTERSPEECH)},
address = {Florence, Italy},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Stuart N. Wrigley; Thomas Hain: Web-Based Automatic Speech Recognition Service - webASR. In: INTERSPEECH 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011, pp. 3265–3268, ISCA, 2011. @inproceedings{DBLP:conf/interspeech/WrigleyH11,
title = {Web-Based Automatic Speech Recognition Service - webASR},
author = {Stuart N. Wrigley and Thomas Hain},
url = {http://www.isca-speech.org/archive/interspeech_2011/i11_3265.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 = {3265--3268},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2010
|
Erfan Loweimi; Seyed Mohammad Ahadi: Objective evaluation of magnitude and phase only spectrum-based reconstruction of the speech signal. In: International Symposium on Communications, Control and Signal Processing, Limassol, Cyprus, 2010. @inproceedings{loweimi_isccsp10,
title = {Objective evaluation of magnitude and phase only spectrum-based reconstruction of the speech signal},
author = {Erfan Loweimi and Seyed Mohammad Ahadi},
year = {2010},
date = {2010-01-01},
booktitle = {International Symposium on Communications, Control and Signal Processing},
address = {Limassol, Cyprus},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Erfan Loweimi; Seyed Mohammad Ahadi: Objective evaluation of phase and magnitude only reconstructed speech: new considerations. In: Information Sciences Signal Processing and their Applications (ISSPA), Kuala Lumpur, Malaysia, 2010. @inproceedings{loweimi_isspa10,
title = {Objective evaluation of phase and magnitude only reconstructed speech: new considerations},
author = {Erfan Loweimi and Seyed Mohammad Ahadi},
year = {2010},
date = {2010-01-01},
booktitle = {Information Sciences Signal Processing and their Applications (ISSPA)},
address = {Kuala Lumpur, Malaysia},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2008
|
Thomas Hain; Asmaa El Hannani; Stuart N. Wrigley; Vincent Wan: Automatic speech recognition for scientific purposes - webASR. In: INTERSPEECH 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008, pp. 504–507, ISCA, 2008. @inproceedings{DBLP:conf/interspeech/HainHWW08,
title = {Automatic speech recognition for scientific purposes - webASR},
author = {Thomas Hain and Asmaa El Hannani and Stuart N. Wrigley and Vincent Wan},
url = {http://www.isca-speech.org/archive/interspeech_2008/i08_0504.html},
year = {2008},
date = {2008-01-01},
booktitle = {INTERSPEECH 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {504--507},
publisher = {ISCA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2006
|
Jean Carletta; Simone Ashby; Sebastien Bourban; Mike Flynn; Mael Guillemot; Thomas Hain; Jaroslav Kadlec; Vasilis Karaiskos; Wessel Kraaij; Melissa Kronenthal; Guillaume Lathoud; Mike Lincoln; Agnes Lisowka; Iain McCowan; Wilfried Post; Denns Reidsma; Pierre Wellner: The AMI meeting corpus: A pre-announcement. In: Machine learning for multimodal interaction, pp. 28–39, Springer, 2006. @incollection{carletta2006amitest,
title = {The AMI meeting corpus: A pre-announcement},
author = {Jean Carletta and Simone Ashby and Sebastien Bourban and Mike Flynn and Mael Guillemot and Thomas Hain and Jaroslav Kadlec and Vasilis Karaiskos and Wessel Kraaij and Melissa Kronenthal and Guillaume Lathoud and Mike Lincoln and Agnes Lisowka and Iain McCowan and Wilfried Post and Denns Reidsma and Pierre Wellner},
year = {2006},
date = {2006-01-01},
urldate = {2006-01-01},
booktitle = {Machine learning for multimodal interaction},
pages = {28--39},
publisher = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
|
Steve Young; Gunnar Evermann; Mark J. F. Gales; Thomas Hain; Dan Kershaw; XA Liu; Gareth Moore; Julian Odell; Dave Ollason; Dan Povey; Valtcho Valtchev; Philip C. Woodland: The HTK book (Version 3.3, Version 3.4). In: 2006. @article{young2006htk,
title = {The HTK book (Version 3.3, Version 3.4)},
author = {Steve Young and Gunnar Evermann and Mark J. F. Gales and Thomas Hain and Dan Kershaw and XA Liu and Gareth Moore and Julian Odell and Dave Ollason and Dan Povey and Valtcho Valtchev and Philip C. Woodland},
year = {2006},
date = {2006-01-01},
urldate = {2006-01-01},
publisher = {Cambridge University Engineering Department, CUED key=young2006htka},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
2005
|
Iain McCowan; Jean Carletta; Wessel Kraaij; Simone Ashby; Sebastien Bourban; Mike Flynn; Maël Guillemot; Thomas Hain; Jaroslav Kadlec; Vasilis Karaiskos; others: The AMI meeting corpus. In: Proceedings of the 5th International Conference on Methods and Techniques in Behavioral Research, vol. 88, 2005. @article{mccowan2005ami,
title = {The AMI meeting corpus},
author = {Iain McCowan and Jean Carletta and Wessel Kraaij and Simone Ashby and Sebastien Bourban and Mike Flynn and Maël Guillemot and Thomas Hain and Jaroslav Kadlec and Vasilis Karaiskos and others},
year = {2005},
date = {2005-01-01},
urldate = {2005-01-01},
journal = {Proceedings of the 5th International Conference on Methods and Techniques in Behavioral Research},
volume = {88},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|