Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Saz, Oscar"'
Huge amounts of digital videos are being produced and broadcast every day, leading to giant media archives. Effective techniques are needed to make such data accessible further. Automatic meta-data labelling of broadcast media is an essential task fo
Externí odkaz:
http://arxiv.org/abs/1606.03333
Autor:
Saz, Oscar, Doulaty, Mortaza, Deena, Salil, Milner, Rosanna, Ng, Raymond W. M., Hasan, Madina, Liu, Yulan, Hain, Thomas
We describe the University of Sheffield system for participation in the 2015 Multi-Genre Broadcast (MGB) challenge task of transcribing multi-genre broadcast shows. Transcription was one of four tasks proposed in the MGB challenge, with the aim of ad
Externí odkaz:
http://arxiv.org/abs/1512.06643
This paper presents a new method for the discovery of latent domains in diverse speech data, for the use of adaptation of Deep Neural Networks (DNNs) for Automatic Speech Recognition. Our work focuses on transcription of multi-genre broadcast media,
Externí odkaz:
http://arxiv.org/abs/1511.05076
Publikováno v:
IEEE Spoken Language Technology Workshop (SLT 2014), pp118-123, 7-10 Dec 2014, Lake Tahoe, NV, USA
This paper presents a novel method for extracting acoustic features that characterise the background environment in audio recordings. These features are based on the output of an alignment that fits multiple parallel background--based Constrained Max
Externí odkaz:
http://arxiv.org/abs/1509.04934
Autor:
Ng, Raymond W. M., Doulaty, Mortaza, Doddipatla, Rama, Aziz, Wilker, Shah, Kashif, Saz, Oscar, Hasan, Madina, AlHarbi, Ghada, Specia, Lucia, Hain, Thomas
Publikováno v:
Proc. of 11th International Workshop on Spoken Language Translation (SLT 2014) 86-91, Lake Tahoe, USA, December 4th and 5th, 2014
The University of Sheffield (USFD) participated in the International Workshop for Spoken Language Translation (IWSLT) in 2014. In this paper, we will introduce the USFD SLT system for IWSLT. Automatic speech recognition (ASR) is achieved by two multi
Externí odkaz:
http://arxiv.org/abs/1509.03870
Publikováno v:
16th Interspeech.Proc. (2015) 2897-2901
Negative transfer in training of acoustic models for automatic speech recognition has been reported in several contexts such as domain change or speaker characteristics. This paper proposes a novel technique to overcome negative transfer by efficient
Externí odkaz:
http://arxiv.org/abs/1509.02409
Publikováno v:
16th Interspeech.Proc. (2015) 3640-3644, Dresden, Germany
Speech recognition systems are often highly domain dependent, a fact widely reported in the literature. However the concept of domain is complex and not bound to clear criteria. Hence it is often not evident if data should be considered to be out-of-
Externí odkaz:
http://arxiv.org/abs/1509.02412
Autor:
Saz, Oscar *, Hain, Thomas
Publikováno v:
In Computer Speech & Language January 2017 41:180-194
Measuring the impact of translation on the accuracy and fluency of vocabulary acquisition of English
Publikováno v:
In Computer Speech & Language May 2015 31(1):49-64
Publikováno v:
In Speech Communication June 2012 54(5):583-600