Search Results - "Gales, M"

Refine Results
  1. 1

    Towards automatic assessment of spontaneous spoken English by Wang, Y., Gales, M.J.F., Knill, K.M., Kyriakopoulos, K., Malinin, A., van Dalen, R.C., Rashid, M.

    Published in Speech communication (01-11-2018)
    “…With increasing global demand for learning English as a second language, there has been considerable interest in methods of automatic assessment of spoken…”
    Get full text
    Journal Article
  2. 2

    Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks by Kastanos, A., Ragni, A., Gales, M. J. F.

    “…Recently, there has been growth in providers of speech transcription services enabling others to leverage technology they would not normally be able to use. As…”
    Get full text
    Conference Proceeding
  3. 3

    Environmentally robust ASR front-end for deep neural network acoustic models by Yoshioka, T., Gales, M.J.F.

    Published in Computer speech & language (01-05-2015)
    “…•Effects of various front-end schemes are examined using DNN acoustic models.•Meeting transcription experiments are conducted using a single distant…”
    Get full text
    Journal Article
  4. 4

    Efficient lattice rescoring using recurrent neural network language models by Liu, X., Wang, Y., Chen, X., Gales, M. J. F., Woodland, P. C.

    “…Recurrent neural network language models (RNNLM) have become an increasingly popular choice for state-of-the-art speech recognition systems due to their…”
    Get full text
    Conference Proceeding
  5. 5

    Recurrent neural network language model training with noise contrastive estimation for speech recognition by Chen, X., Liu, X., Gales, M. J. F., Woodland, P. C.

    “…In recent years recurrent neural network language models (RNNLMs) have been successfully applied to a range of tasks including speech recognition. However, an…”
    Get full text
    Conference Proceeding
  6. 6

    Bi-directional Lattice Recurrent Neural Networks for Confidence Estimation by Li, Q., Ness, P. M., Ragni, A., Gales, M. J. F.

    “…The standard approach to mitigate errors made by an automatic speech recognition system is to use confidence scores associated with each predicted word. In the…”
    Get full text
    Conference Proceeding
  7. 7
  8. 8

    Ensemble Distillation Approaches for Grammatical Error Correction by Fathullah, Y., Gales, M.J.F., Malinin, A.

    “…Ensemble approaches are commonly used techniques to improving a system by combining multiple model predictions. Additionally these schemes allow the…”
    Get full text
    Conference Proceeding
  9. 9

    Noisy Constrained Maximum-Likelihood Linear Regression for Noise-Robust Speech Recognition by Kim, D K, Gales, M J F

    “…Adaptive training is a widely used technique for building speech recognition systems on nonhomogeneous training data. Recently, there has been interest in…”
    Get full text
    Journal Article
  10. 10
  11. 11
  12. 12

    The Role of Histopathologic Subtype in the Setting of Hippocampal Sclerosis-Associated Mesial Temporal Lobe Epilepsy by Gales, Jordan M., BS, Jehi, Lara, MD, Nowacki, Amy, PhD, Prayson, Richard A., MD MEd

    Published in Human pathology (01-05-2017)
    “…Summary Hippocampal sclerosis (HS) and focal cortical dysplasia (FCD) are among the most common neuropathological findings in those undergoing surgery for…”
    Get full text
    Journal Article
  13. 13

    Maximum likelihood linear transformations for HMM-based speech recognition by Gales, M.J.F.

    Published in Computer speech & language (01-04-1998)
    “…This paper examines the application of linear transformations for speaker and environmental adaptation in an HMM-based speech recognition system. In…”
    Get full text
    Journal Article
  14. 14

    Issues with uncertainty decoding for noise robust automatic speech recognition by Liao, H., Gales, M.J.F.

    Published in Speech communication (01-04-2008)
    “…Interest continues in a class of robustness algorithms for speech recognition that exploit the notion of uncertainty introduced by environmental noise. These…”
    Get full text
    Journal Article
  15. 15

    Unicode-based graphemic systems for limited resource languages by Gales, M. J. F., Knill, K. M., Ragni, A.

    “…Large vocabulary continuous speech recognition systems require a mapping from words, or tokens, into sub-word units to enable robust estimation of acoustic…”
    Get full text
    Conference Proceeding
  16. 16

    Discriminative classifiers with adaptive kernels for noise robust speech recognition by Gales, M.J.F., Flego, F.

    Published in Computer speech & language (01-10-2010)
    “…Discriminative classifiers are a popular approach to solving classification problems. However, one of the problems with these approaches, in particular kernel…”
    Get full text
    Journal Article
  17. 17

    PHONETIC AND GRAPHEMIC SYSTEMS FOR MULTI-GENRE BROADCAST TRANSCRIPTION by Wang, Y., Chen, X., Gales, M. J. F., Ragni, A., Wong, J. H. M.

    “…State-of-the-art English automatic speech recognition systems typically use phonetic rather than graphemic lexicons. Graphemic systems are known to perform…”
    Get full text
    Conference Proceeding
  18. 18

    CUED-RNNLM - An open-source toolkit for efficient training and evaluation of recurrent neural network language models by Chen, X., Liu, X., Qian, Y., Gales, M. J. F., Woodland, P. C.

    “…In recent years, recurrent neural network language models (RNNLMs) have become increasingly popular for a range of applications including speech recognition…”
    Get full text
    Conference Proceeding Journal Article
  19. 19

    Paraphrastic language models by Liu, X., Gales, M.J.F., Woodland, P.C.

    Published in Computer speech & language (01-11-2014)
    “…•Paraphrastic language models proposed.•Statistical paraphrase learning from standard texts.•Improved LM context coverage and generalization…”
    Get full text
    Journal Article
  20. 20

    Improving the training and evaluation efficiency of recurrent neural network language models by Chen, X., Liu, X., Gales, M. J. F., Woodland, P. C.

    “…Recurrent neural network language models (RNNLMs) are becoming increasingly popular for speech recognition. Previously, we have shown that RNNLMs with a full…”
    Get full text
    Conference Proceeding