Unsupervised data selection for speech recognition with contrastive loss ratios
This paper proposes an unsupervised data selection method by using a submodular
function based on contrastive loss ratios of target and training data sets. A model using a …
function based on contrastive loss ratios of target and training data sets. A model using a …
Data-selective transfer learning for multi-domain speech recognition
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 …
reported in several contexts such as domain change or speaker characteristics. This paper …
Automatic genre and show identification of broadcast media
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 …
giant media archives. Effective techniques are needed to make such data accessible further …
[PDF][PDF] Investigating continuous space language models for machine translation quality estimation
We present novel features designed with a deep neural network for Machine Translation
(MT) Quality Estimation (QE). The features are learned with a Continuous Space Language …
(MT) Quality Estimation (QE). The features are learned with a Continuous Space Language …
Latent dirichlet allocation based organisation of broadcast media archives for deep neural network adaptation
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 …
data, for the use of adaptation of Deep Neural Networks (DNNs) for Automatic Speech …
Unsupervised domain discovery using latent dirichlet allocation for acoustic modelling in speech recognition
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 …
the literature. However the concept of domain is complex and not bound to clear criteria …
Shefce: A Cantonese-English bilingual speech corpus for pronunciation assessment
This paper introduces the development of ShefCE: a Cantonese-English bilingual speech
corpus from L2 English speakers in Hong Kong. Bilingual parallel recording materials were …
corpus from L2 English speakers in Hong Kong. Bilingual parallel recording materials were …
Automatic quality estimation for speech translation using joint ASR and MT features
This paper addresses the automatic quality estimation of spoken language translation (SLT).
This relatively new task is defined and formalized as a sequence-labeling problem where …
This relatively new task is defined and formalized as a sequence-labeling problem where …
Quality estimation for ASR K-best list rescoring in spoken language translation
Spoken language translation (SLT) combines automatic speech recognition (ASR) and
machine translation (MT). During the decoding stage, the best hypothesis produced by the …
machine translation (MT). During the decoding stage, the best hypothesis produced by the …
[PDF][PDF] A study on the stability and effectiveness of features in quality estimation for spoken language translation.
A quality estimation (QE) approach informed with machine translation (MT) and speech
recognition (ASR) features has recently shown to improve the performance of a spoken …
recognition (ASR) features has recently shown to improve the performance of a spoken …