Organized by ISCA-SAC, the 3rd Doctoral Consortium was held on Sunday, August 20th, 2017 at the Royal Institute of Technology (KTH), Stockholm, Sweden.

 

The Doctoral Consortium provides students an opportunity to present their PhD projects to experts and peers and receive valuable feedback on research plans as well as interesting new ideas. This forum provides an invaluable and enriching experience for the students.

Board of experts:

  • Tanja Schultz (Universität Bremen)
  • Christophe d’Alessandro (LIMSI)
  • Anne Cutler (Max Planck Institute for Psycholinguistics)
  • Jon Barker (University of Sheffield)
  • Thomas Hain (University of Sheffield)
  • Dilek Hakkani-Tür (Google Inc.)
  • Karen Livescu (TTIC)

 

The agenda and abstracts for each of the presentations are available for download:

  Attachment   Size
Agenda 3rd Doctoral Consortium   71.31 KB
Mohammed Salah Al-Radhi - High Quality Continuous Residual-based Vocoder for Statistical Parametric Speech Synthesis   330.81 KB
Nitya Tiwari - Speech Enhancement Using Noise Estimation with Adaptive Dynamic Quantile Tracking for Use in Hearing Aids   721.38 KB
Malin Svensson Lundmark - Intra-syllabic structures of articulatory gestures in Swedish prosody   292.71 KB
Basil Abraham - Cross-lingual Techniques and Use of Articulatory Features in Acoustic Modeling of Low-Resource Languages   494.027 KB
Julia Forsberg - Urban adolescents in interaction in their L1 and L2: production, perception and the evaluation of a data collection method   205.18 KB
Jeremy H. M. Wong - An analysis of student-teacher information propagation   36.72 KB
Carolina De Pasquale - Depression Diagnosis and Treatment Through Speech (DDaTTS)   74.8 KB
Pablo Brusco - Neural correlates of spoken language processing   89.15 KB
P. Gangamohan - Analysis of Emotional Speech using Excitation Source Information   1000.76 KB
Bidisha Sharma - Scope of Sonority Information in Statistical Parametric Speech Synthesis   68.76 KB
RaviShankar Prasad - Analysis of dynamics of vocal tract system using zero time windowing method   981.64 KB
Rohan Kumar Das - Incorporating Source Features, Acoustic-phonetic Information and Suitable Pattern Recognition Approach for Limited Test Data Speaker Verification   36.85 KB