[Univ of Cambridge] [Dept of Engineering]

Anton Ragni - Publications

  • Conference papers

    • D. Oard, P. Galuscakova, K. McKeown, M. Carpuat, R. Eskander, K. Heafield, E. Kayi, C. Kedzie, S. Muresan, S. Nair, X. Niu, D. Radev, A. Ragni, H.-C. Shing, Y. Virin, W. Xu, R. Zhang, E. Zotkina, J. Barrow, M.J.F. Gales, "Surprise Languages: Rapid-Response Cross-Language IR", EVIA, 2019; pdf
    • Q. Li, P.M. Ness, A. Ragni, M.J.F. Gales, "Bi-Directional Lattice Recurrent Neural Networks for Confidence Estimation", ICASSP, 2019; pdf
    • A. Ragni, M.J.F. Gales, "Automatic Speech Recognition System Development in the 'Wild'", Interspeech, 2018; pdf
    • O. Chen, A. Ragni, M.J.F. Gales, X. Chen, "Active Memory Networks for Language Modeling", Interspeech, 2018; pdf
    • K.M. Knill, M.J.F. Gales, K. Kyriakopoulos, A. Malinin, A. Ragni, Y. Wang, A. Caines, "Impact of ASR Performance on Free Speaking Language Assessment", Interspeech, 2018;
    • Y. Wang, X. Chen, M.J.F. Gales, A. Ragni, J.H.M. Wong, "Phonetic and graphemic systems for multi-genre broadcast trancription", ICASSP, 2018; pdf
    • M.J.F. Gales, K.M. Knill, A. Ragni, "Low-Resource Speech Recognition and Keyword-Spotting", SPECOM, 2017
    • X. Chen, A. Ragni, X. Liu, M.J.F. Gales, "Investigating Bidirectional Recurrent Neural Network Language Models for Speech Recognition", Interspeech, 2017; pdf
    • K.M. Knill, M.J.F. Gales, K. Kyriapolous, A. Ragni, Y. Wang, "Use of Graphemic Lexicons for Spoken Language Assessment", Interspeech, 2017;
    • A. Malinin, A. Ragni, M.J.F. Gales, K.M. Knill, "Incorporating Uncertainty into Deep Learning for spoken language assessment", ACL, 2017; pdf
    • A. Malinin, K.M. Knill, A. Ragni, Y. Wang, M.J.F. Gales, "An attention based model for off-topic spontaneous spoken response detection: An Initial Study", SLaTE, 2017;
    • A. Ragni, D. Saunders, P. Zahemszky, J. Vasilakes, M.J.F. Gales, K.M. Knill, "Morph-to-Word Transduction for Accurate and Efficient Automatic Speech Recognition and Keyword Search", ICASSP, 2017; pdf
    • A. Ragni, C. Wu, M.J.F. Gales, J. Vasilakes, K.M. Knill, "Stimulated Training for Automatic Speech Recognition and Keyword Search in Limited Resource Conditions", ICASSP, 2017; pdf
    • X. Chen, A. Ragni, J. Vasilakes, X. Liu, K.M. Knill, M.J.F Gales, "Recurrent Neural Network Language Models for Keyword Search", ICASSP, 2017; pdf
    • A. Ragni, E. Dakin, X. Chen, M.J.F. Gales, K.M. Knill, "Multi-Language Neural Network Language Models", Interspeech, 2016; pdf
    • J. Yang, A. Ragni, M.J.F. Gales, K.M. Knill, "Log-linear System Combination Using Structured Support Vector Machines", Interspeech, 2016.
    • J. Yang, C. Zhang, A. Ragni, M.J.F. Gales, P.C. Woodland, "System Combination with Log-Linear Models", ICASSP, 2016.
    • H. Wang, A. Ragni, M.J.F. Gales, K.M. Knill, P.C. Woodland, C. Zhang, "Joint decoding of tandem and hybrid systems for improved keyword spotting on low resource languages", Interspeech, 2015; pdf
    • G. Mendels, E. Cooper, V. Soto, J. Hirschberg, M.J.F. Gales, K.M. Knill, A. Ragni, H. Wang, "Improving speech recognition and keyword search for low resource languages using web data", Interspeech, 2015; pdf
    • A. Ragni, M.J.F. Gales, K.M. Knill, "A language space representation for speech recognition", ICASSP, 2015; pdf
    • M.J.F. Gales, K.M. Knill, A. Ragni, "Unicode-based graphemic systems for limited resource languages", ICASSP, 2015; pdf
    • A. Ragni, K.M. Knill, S.P. Rath, M.J.F. Gales, "Data augmentation for low resource languages", Interspeech, 2014; pdf
    • K.M. Knill, M.J.F. Gales, A. Ragni, S.P. Rath, "Language independent and unsupervised acoustic models for speech recognition and keyword spotting", Interspeech, 2014; pdf
    • S.P. Rath, K.M. Knill, A. Ragni, M.J.F. Gales, "Combining tandem and hybrid systems for improved speech recognition and keyword spotting on low resource languages", Interspeech, 2014; pdf
    • T. Yoshioka, A. Ragni, M.J.F. Gales, "Investigation of unsupervised adaptation of DNN acoustic models with filter-bank input", ICASSP, 2014; pdf
    • R.C. van Dalen, A. Ragni, M.J.F. Gales, "Efficient Decoding with Generative Score-Spaces Using the Expectation Semiring", ICASSP, 2013; pdf
    • Z. Roupakia, A. Ragni, M.J.F. Gales, "Rapid nonlinear speaker adaptation for large-vocabulary speech recognition", INTERSPEECH, 2012; pdf
    • A. Ragni, M.J.F. Gales, "Inference algorithms for generative score-spaces", ICASSP, 2012; pdf
    • A. Ragni, M.J.F. Gales, "Structured discriminative models for noise robust continuous speech recognition", ICASSP, 2011; pdf

  • Workshop papers

    • X. Chen, X.Liu, A. Ragni, Y. Wang, M.J.F. Gales, "Future Word Contexts in Neural Network Language Models", ASRU, 2017; pdf
    • R.C. van Dalen, J. Yang, H. Wang, A. Ragni, C. Zhang, M.J.F Gales, "Structured Discriminative Models Using Deep Neural-Network Features", ASRU, 2015;
    • J. Cui, B. Kingsbury, B. Ramabhadran, A. Sethy, K. Audhkhasi, X. Cui, E. Kislal, L. Mangu, M. Nussbaum-Thom, M. Picheny, Z. Tuske, P. Golik, R. Schluter, H. Ney, M.J.F. Gales, K.M. Knill, A. Ragni, H. Wang, P. Woodland, "Multilingual representations for low resource speech recognition and keyword search", ASRU, 2015;
    • M.J.F. Gales, K.M. Knill, A. Ragni, S.P. Rath, "Speech recognition and keyword spotting for low resource Languages: BABEL project research at CUED", SLTU, 2014; pdf
    • A. Ragni, M.J.F. Gales, "Derivative kernels for noise robust ASR", ASRU, 2011; pdf; Best Student Paper Award [1],[2]
    • M.J.F. Gales, A. Ragni, H. AlDamarki, C. Gautier, "Support vector machines for noise robust ASR", ASRU, 2009; pdf

  • Journal articles

    • C. Wu, M.J.F. Gales, A. Ragni, P. Karanasou, K.C. Sim, "Improving Interpretability and Regularization in Deep Learning", IEEE TASLP, vol 26, no 2, pp. 256-265, 2018
    • S.-X. Zhang, A. Ragni, M.J.F. Gales, "Structured log-linear models for noise robust speech recognition", Signal Processing Letters, 2011; pdf

  • Technical reports

    • R.C. van Dalen, A. Ragni, M.J.F. Gales, "Efficient decoding with continuous rational kernels using the expectation semiring", CUED/F-INFENG/TR.674, 2012; pdf

  • Patents

    • A. Ragni, K.K. Chin, "Speech recognition utilising a hybrid combination of probabilities output from a language model and an acoustic model", GB2463908, 2010; link
    • K.K. Chin, A. Ragni, "Speech recognition utilising determination of a back-off group of code words in using an acoustic model", GB2463909, 2010; link

  • Theses

    • A. Ragni, "Discriminative models for speech recognition", Cambridge University, 2013; pdf