5th Doctoral Consortium Abstracts

Organized by ISCA-SAC, the 5th Doctoral Consortium was held on Sunday, September 14th, 2019 in Graz, Austria.

 

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:

  • Kate Knill (University of Cambridge)
  • Anouschka Foltz (University of Graz)
  • João Freitas (DefinedCrowd)
  • Ngoc Thang Vu (University of Stuttgart)
  • Hema Murthy (Indian Institute of Technology Madras)
  • Simon King (University of Edinburgh)
  • Sebastian Möller (Technical University of Berlin)
  • Dayana Ribas (University of Zaragoza)
  • Kyu Han (ASAPP)

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

 

  Attachment   Size
Agenda 5th Doctoral Consortium   71.31 KB
Protima Nomo Sudro - Intelligibility Enhancement of Cleft Lip and Palate Speech   330.81 KB
Lorenz Diener - The Impact of Audible Feedback on EMG-to-Speech Conversion   721.38 KB
Purvi Agrawal - Unsupervised Representation Learning for Robust Speech Recognition   292.71 KB
Grandee Lee - Cross-lingual Natural Language Modeling   494.027 KB
Anusha Prakash - End-To-End Speech Synthesis for Indian Languages   205.18 KB
Thilo Michael - Simulation of Conversational Behavior during Impaired Audio Transmissions   36.72 KB
Xiaxue Gao - Speaker-Independent Speech-to-Singing Conversion and Singing Synthesis   74.8 KB
Meysam Shamsi - Script Optimization for the Expressive Synthesis of Audio-books   89.15 KB
Yi Zhou - Many-to-many Cross-lingual Voice Conversion using Bilingual Phonetic PosteriorGram by an Average Modeling Approach   1000.76 KB
Sai Krishna Rallabandi - On Controlled DeEntaglement for Natural Language Processing   68.76 KB
Mingyang Zhang - Shared model for multi-source speech generation tasks   981.64 KB
Bhanu Teja Nellore - Applying production knowledge for speech signal processing   36.85 KB
Per Fallgren - Utilising large quantities of found speech data   981.64 KB
Seung Hee Yang - Automatic Speech Recognition-enabled Pronunciation Learning System Development for Second Language Speakers of Korean   36.85 KB

 

 

6th Doctoral Consortium Abstracts

Organized by ISCA-SAC, the 6th Doctoral Consortium was remotely held on Saturday, 24 October 2020.

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:

  • Amalia Arvaniti (Radboud University, Netherlands)
  • Gerard Bailly (GIPSA-lab, CNRS, France)
  • Nicholas Cummins (King’s College London, UK)
  • Julia Hirschberg (Columbia University, USA)
  • Shrikanth Narayanan (University of Southern California, USA)
  • Yao Qian (Microsoft Research, USA)
  • Andrew Wedel (University of Arizona, USA)
  • Jinsong Zhang (Beijing Language And Culture University, China)

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

  Attachment
Sin Yu Bonnie Ho - Optimization of the data processing pipeline for pseudo-words in phonetics research
Siddique Latif - Deep Representation Learning for Improving Speech Emotion Recognition
Rahul Jaiswal - Towards a Non-Intrusive Context-Aware Speech Quality Model
Kamini Sabu - Automatic assessment of children’s oral reading skills
Haoxin Ma - Hypersphere Embedding and Additive Margin for Query-by-example Keyword Spotting
Bin Zhao - Temporal-Spatial-Spectral Investigation of Brain Network Dynamics in Human Speech Perception and Production
Rini A Sharon - Neural decoding of continuous speech EEG signals
Wei Xue - Developing Valid Measurement Procedures for Speech Intelligibility of Pathological Speech
Lei Xi - French Prosodic Phrasing in Chinese Learners: ERP studies
Sai Sirisha Rallabandi - A framework to incorporate aspects of social perception in synthetic voices
Badr M. Abdullah - Making Sense of What Sounds Similar: Modelling Mutual Intelligibility among Related Languages

 

 

Page 8 of 8