You are here

Natural Speech Technology Annual Meeting 2015

28 May 2015 -  University of Cambridge, Engineering Department 


The discussion for dissertation and other documents are still rather popular among our clients. You have to register in order to get an access to them.

09:00 - 09:30
 - Startup and coffee

09.30 - 11.20 Talks 
  • Steve Renals - Introduction [pdf]
  • Penny Karanasou  "Progress in Adaptation of DNN-based Acoustic Models" [pdf]
    • Pawel Swietojanski  "An overview of DNN adaptation methods for ASR Systems within NST project"
    • Zhizheng Wu  "An overview of DNN adaptation methods for TTS Systems within NST project"
  • Peter Bell  "The MGB Challenge at IEEE ASRU-2015" [pdf]
  • One minute madness (introduction of demos/posters in next session) [pdf]

11.20 - 13:00 Coffee and demos/posters  

  1. Pawel Swietojanski "Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models"
  2. Yulan Liu/Penny Karanasou "An investigation into speaker informed DNN front-end for LVCSR" [pdf]
  3. Yulan Liu "On the relationship between speaker informed DNN training and linear DNN input normalisation" [pdf]
  4. Penny Karanasou "I-Vector estimation using informative priors for adaptation of deep neural networks" [pdf]
  5. Chunyang Wu "Multi-basis Adaptive Neural Network for Rapid Adaptation in Speech Recognition"
  6. Peter Bell "The UEDIN ASR Systems for the IWSLT 2014 Evaluation"
  7. Siva Reddy Gangireddy "Prosodically-enhanced recurrent neural network language models" [pdf]
  8. Yanmin Qian "Noise-aware structured DNN for robust ASR"
  9. Liang Lu "A study of the RNN encoder-decoder for large vocabulary ASR"
  10. Mortaza Doulaty "Unsupervised domain discovery" [pdf]
  11. Chao Zhang "A general ANN extension for HTK" [pdf]
  12. Liang Lu / Pawel Swietojanski / Peter Bell "Kaldi extensions at Edinburgh"
  13. Marcus Tomalin "Inserting filled pauses and discourse markers for disfluent speech synthesis" [pdf]
  14. Mirjam Wester/Gustav Eje Henter "On the subjective evaluation of synthetic speech: are we using enough listeners?" [pdf]
  15. Oliver Watts "Sentence-level control vectors for deep neural network speech synthesis" [pdf]
  16. Tom Merritt "Deep neural network context embeddings for model selection in rich-context HMM synthesis" [pdf]
  17. Zhizheng Wu "“Deep neural networks employing multi-task learning and stacked bottleneck features for speech synthesis”
  18. Pierre Lanchantin "Details of the MGB Challenge data preparation" [pdf]
  19. Pierre Lanchantin/ Christophe Veaux "Reconstructing voices within the multiple-average-voice-model framework" [pdf]
  20. Phil Green "Browsing Oral History: English Heritage Demo"[pdf]
  21. Mauro Nicolao/Salil Deena "Automatic speech recognition for people with disordered speech: results from online and offline experiments" [pdf]
  22. Qiang Huang "User dependent interactive system using multimodal information"
  23. Peter Bell "GlobalVox Demo"

‚Äč13:00 - 14.15 Lunch 

14.15- 15.15 Talks 
  • Thomas Hain - Corpora: new collections and structuring diverse data 
  • Christophe Veaux "Voice banking and voice reconstruction"  [pdf]
  • Andrew Liu "Recent improvements in training, adaptation and decoding using RNNLMs" 
15.15 - 15.45 Afternoon coffee
15.45 - 16:45 Discussions  
  • Clinical (kicked off by Stuart Cunningham)
  • Media (kicked off by Phil Woodland)
  • Future Challenges (kicked off by Simon King) 
16:45  Wrap-up
17.00 - 18:30 Advisory board meeting
19:30  Dinner at Emmanuel College

A few photos taken during the meeting (all photo credits: Mauro Nicolao)