You are here

Posters Annual Meeting 2016

  1. Peter Bell "CD-DNN regularisation with multitask learning"
  2. Peter Bell "WFST-based alignment for broadcast media"
  3. Mauro Nicolao "Experimental results on online and offline dysarthric speech recognition"
  4. Bilal Khaliq "Segmentwise language model interpolation for lightly supervised alignment of broadcast subtitles"
  5. Salil Deena "Combining Feature and Model-Based Adaptation of RNNLMs for Multi-Genre Broadcast Speech Recognition"
  6. Oscar Saz "The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media"
  7. Oscar Saz "The 2015 Sheffield system for longitudinal diarisation of broadcast media"
  8. Raymond Ng "Groupwise learning for ASR k-best list reranking in spoken language translation"
  9. Pawel Swietojanski "Model based adaptation of CD-DNN acoustic models with LHUC and differentiable pooling operators"
  10. Cassia Valentini-Botinhao "Speech Enhancement for Noise-Robust Text-To-Speech using Deep Recurrent Neural Networks"
  11. Srikanth Ronanki "A template-based approach for speech synthesis intonation generation using LSTMs"
  12. Gustav Eje Henter "Robust text-to-speech duration modelling using DNNs" 
  13. Mirjam Wester "Comprehension of synthetic speech with and without natural prosody"
  14. Mirjam Wester "Artificial Personality and Disfluency"
  15. Madina Hasan "Noise-matched training of CRF based sentence end detection models"
  16. Chao Zhang "DNN Speaker Adaptation using Parameterised Sigmoid and ReLU Hidden Activation Functions"
  17. Chao Zhang "System Combination with Log-linear Models"
  18. Linlin Wang "Improved DNN-based Segmentation for Multi-genre Broadcast Audio"
  19. Yanmin Qian "Integrated Adaptation with Multi-factor Joint-Learning for Far-Field Speech Recognition"
  20. Phil Woodland "Cambridge University Transcription Systems for the Multi-Genre Broadcast Challenge: Updated Results"
  21. Linlin Wang "Speaker Diarisation and Longitudinal Linking in Multi-Genre Broadcast Data"
  22. Pierre Lanchantin "The Development of the Cambridge University Alignment Systems for the Multi-Genre Broadcast Challenge"
  23. Yanmin Qian "Very Deep Convolutional Neural Networks for Noise Robust Speech Recognition"
PDF icon art_pers_poster_IS.pdf
PDF icon speech_prosody.pdf
PDF icon SwietojanskiNST.pdf
PDF icon CassiaUKSpeech16_flat.pdf
PDF icon multilingualTTS.pdf