2015

[1] Y. Hifny, Unified acoustic modeling using deep conditional random fields, Transactions on Machine Learning and Artificial Intelligence (TMLAI), vol. 3, no. 2, pp. 65-84, 2015. [ bib | pdf | html ]
[2] Y. Hifny, Frame based postprocessor for speech recognition based on augmented conditional random fields, Transactions on Machine Learning and Artificial Intelligence (TMLAI), vol. 3, no. 2, pp. 23-33, 2015. [ bib | pdf | html ]

2013

[1] Y. Hifny, Restoration of arabic diacritics using dynamic programming, in The 2013 8th International Conference on Computer Engineering & Systems (ICCES’2013), 2013. [ bib | pdf ]
[2] Y. Hifny, Augmented conditional random fields modeling based on discriminatively trained features, in Proc. INTERSPEECH, 2013. [ bib | pdf ]
[3] Y. Hifny, Acoustic modeling based on deep conditional random fields, in Deep Learning for Audio, Speech and Language Processing, ICML, 2013. [ bib | pdf ]
[4] Y. Hifny, Deep learning using a Manhattan update rule, in Deep Learning for Audio, Speech and Language Processing, ICML, 2013. [ bib | pdf ]

2012

[1] Y. Hifny, Smoothing techniques for arabic diacritics restoration, in The Twelfth ESOLE Conference on Language Engineering (ESOLEC'12), 2012. [ bib | pdf ]
[2] Y. Hifny, Higher order n-gram language models for arabic diacritics restoration, in The Twelfth ESOLE Conference on Language Engineering (ESOLEC'12)., 2012. [ bib | pdf ]

2009

[1] Y. Hifny and S. Renals, Speech recognition using augmented conditional random fields, IEEE Transactions on Audio, Speech and Language Processing, vol. 17, no. 2, pp. 354-365, 2009. [ bib | pdf | html ]
[2] J. Yamagishi, T. Nose, H. Zen, Z. Ling, T. Toda, K. Tokuda, S. King, and S. Renals, Robust speaker-adaptive HMM-based text-to-speech synthesis, IEEE Transactions on Audio, Speech and Language Processing, vol. 17, no. 6, pp. 1208-1230, 2009. The auther of the gender mixing modeling idea . [ bib | pdf | html ]

2008

[1] Y. Hifny and Y. Gao, Discriminative training using the trusted expectation maximization, in In Proceedings of Interspeech, pp. 948-951, 2008. [ bib | pdf ]

2006

[1] Y. Hifny, Conditional Random Fields for Continuous Speech Recognition. PhD thesis, University of Sheffield, UK, 2006. [ bib | pdf ]

2005

[1] Y. Hifny and S. Renals, Acoustic modelling based on conditional random field, in 2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms, (Edinburgh, UK), July 2005. [ bib ]
[2] Y. Hifny, S. Renals, and N. Lawrence, A hybrid MaxEnt/HMM based ASR system, in Proc. INTERSPEECH, (Lisbon, Portugal), pp. 3017-3020, 2005. [ bib | pdf ]

2004

[1] Y. Hifny, S. Renals, and N. D. Lawrence, Acoustic space dimensionality selection and combination using the maximum entropy principle, in Proc. IEEE ICASSP, vol. 5, (Montreal, Canada), pp. 637-640, May 2004. [ bib | pdf ]

2003

[1] Y. Hifny and et al., ARABTALK: An implementation for arabic text to speech system, in In Proceedings of the 4th conference of the Egyptian Society of Language Engineering (ESLE), October 2003. [ bib | pdf ]

2002

[1] Y. Hifny, Generalized improved iterative scaling for random field parameters estimation. September 2002. [ bib | pdf ]
[2] Y. Hifny and M. Rashwan, Duration modelling for arabic text to speech synthesis, in In Proceedings of ICSLP2002, (Denver, Colorado, USA), pp. 1773-1776, September 2002. [ bib | pdf ]

2000

[1] Y. Hifny, Online arabic handwriting recognition, Master's thesis, University of Cairo, Egypt, 2000. [ bib ]