I am a research scholar working at the Speech and Vision Lab, IIIT-Hyderabad.

I work under the supervision of Prof. B. Yegnanarayana.

My work is oriented towards understanding the production system dynamics during the production of certain sounds.

I attempt to study the changes in the vocal tract acoustic system response with respect to the movement of different articulators.

My first project; Virtual Labs; www.vlab.co.in; requires me to develop a virtual online platform for students to conduct experiments in the field of Artificial Neural Networks. I developed the lab, with the help of my lab members, using Java platform and basic knowledge of Neural Networks. 

My Second project; Prosodically guided phonetic engine; constitutes my current major research area. I am working towards segmenting speech signals into basic units using signal processing tools, which can later be used for labeling the segments with accurate boundaries. 

1. Ravi Shankar Prasad and B. Yegnanarayana, "Determination of glottal open regions by exploiting changes in the vocal tract system characteristics", 2016. [More] [Digital]
2. Ravi Shankar Prasad and B. Yegnanarayana, "Robust pitch estimation in noisy speech using ZTW and group delay function", 2015. [More] [Digital]
3. Ravi Shankar Prasad and B. Yegnanarayana, "Acoustic segmentation of speech using zero time liftering (ZTL)", 2013. [More] [Digital]