About me


Srikanth Ronanki is a PhD student at CSTR, University of Edinburgh working under the supervision of Dr. Rob Clark and Prof. Simon King. He is currently living in Edinburgh, United Kingdom. He did BTech in Electronics and communications engineering (ECE) from IIIT-Hyderabad in 2011, MS (by Research) in 2014 from Dept. of ECE, IIIT-Hyderabad with specialization in Speech and Vision under the guidance of Dr. Kishore Prahallad. His areas of research interest include Speech Synthesis, Speech-To-Speech Translation and Statistical methods in Artificial Intelligence.

Goal: To design a speech-to-speech translation system without the need for speech decoding or any orthographic transcriptions.

Timeline

Oct 21, 2014: Moved to Edinburgh, UK to pursue PhD at CSTR, University of Edinburgh.

Jan 06, 2014: Working as Data Scientist at iLabs [24]7 inc.

Sep 08, 2013: Worked with an open-source organization named Ankur-India as an intern from Google Summer of Code (GSoC) on Indian languages Interactive Voice Response System (Indic-IVRS) using CMUSphinx Speech Recognition and Festival/Festvox Text-To-Speech systems.

Apr 30, 2013: Worked on Syllable based models for prosody in HMM based speech synthesis as a part of Simple4All project at Center for Speech Technology Research, University of Edinburgh

Aug 10, 2012: Worked with an open-source organization named CMUSphinx as an intern from Google Summer of Code (GSoC) on Pronunciation Evaluation using CMUSphinx Speech Recognition.

May 31, 2012: Working as a Research Scholar in Speech and Vision Lab (SVL) at IIIT-Hyderabad.