VT

Vivek Tyagi

CeADAR, LinkedIn, École Polytechnique Fédérale de Lausanne, Indian Institute of Technology Kanpur, Xerox Research Center India

ORCID iD 0000-0002-3067-0801
Follow

About

Vivek Tyagi is a senior research scientist at CeADAR, University College Dublin. CeADAR is Ireland’s national centre for Applied AI. CeADAR is a market-focused technology centre that drives the accelerated research, development, and deployment of AI and data analytics technology and innovation into businesses.
Vivek obtained his PhD degree in speech recognition from the Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland and his Bachelor of Technology degree in Electrical Engineering from the Indian Institute of Technology (IIT) Kanpur. His research interests are in deep learning for speech recognition, natural language processing (NLP), biometrics, social media content moderation and in general Speech, Text, Vision AI enabled novel products for communications and collaboration. He is a senior member of IEEE and has published about 35 peer-reviewed papers in IEEE ICASSP, ISCA Interspeech, IEEE CVPR Workshops on Biometrics, IEEE ICPR, Elsevier Speech Communication Journal and IEEE Trans on Intelligent Transportation Systems. He has been granted about 12 patents in machine learning and speech recognition applications. In the past he has been a senior researcher/manager at LinkedIn Text-AI, Xerox Research India and IBM Research India. He is a Senior Member of IEEE and co-winner of the ISCA Award for the best paper published in the Speech Communication Journal (2006-2008): "Automatic speech recognition and speech variability: A Review".

Employment

  • CeADAR Sr. Research Scientist
    2021 - Present
  • LinkedIn Text AI Staff Researcher/Manager
    2018 - 2021
  • Xerox Research Center India Senior Researcher/Manager
    2013 - 2016
  • Interactive Intelligence Inc Senior Researcher
    2011 - 2013
  • IBM Research India Research Scientist
    2006 - 2011

Education

  • École Polytechnique Fédérale de Lausanne PhD
    2001 - 2006
  • Indian Institute of Technology Kanpur Bachelor of Technology
    1997 - 2001

Projects & Funding

Projects & funding information is unavailable.

Publications (46)

  • Method and system for acoustic data selection for training the parameters of an acoustic model
    2018
    +Save
  • Method and system for acoustic data selection for training the parameters of an acoustic model
    2018
    +Save
  • Method and system for detecting sentiment by analyzing human speech
    2017
    +Save
  • Methods and systems for identifying keywords in speech signal
    2017
    +Save
  • Method and system for selectively biased linear discriminant analysis in automatic speech recognition systems
    2017
    +Save
  • Deep triphone embedding improves phoneme recognition
    arXiv 2017
    +Save
  • System and method for learning alternate pronunciations for speech recognition
    2016
    +Save
  • Hybrid context dependent CD-DNN-HMM Keyword Spotting (KWS) in speech conversations
    IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 DOI: 10.1109/MLSP.2016.7738862
    +Save
  • Novel acoustic features for automatic dialog-act tagging
    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2016 DOI: 10.1109/ICASSP.2016.7472850
    +Save
  • Xerox Conversational AI Agent (XCAI) for Enterprise Knowledgebase Q&A
    2016
    +Save