Alok Ulhas Parlikar

Research Interests

  • Speech Synthesis: Text Processing, Speaking Styles, Prosody, Singing
  • Automatic Speech Recognition
  • Speech to Speech Translation
  • Multilingual Speech and Language Processing
  • Error Analysis and Visualization Tools
  • Practical Implementations of Speech and Language Technologies

Experience

Amazon.com, USA (Nov 2013 – Nov 2014)

I was part of Amazon's speech group that works on speech and language solutions for revolutionalizing how customers interact with Amazon's products and services. Projects such as Echo, Dash, Fire TV and the Mobile Shopping App are illustrative use cases.

I am an author on two pending US patent applications submitted by Amazon.

Volunteering

I spend some of my spare time on android app and text-to-speech voices for Indian languages, thus supporting non-profit efforts to increase literacy for the visually impaired in India.

Education

PhD in Language and Information Technologies
Carnegie Mellon University, Sep 2013

Thesis: Style-Specific Phrasing in Speech Synthesis [pdf]
Advisor: Alan W Black

Graduate Research Experience

While at Carnegie Mellon, I have worked on several projects in the area of multilingual speech and language processing. Here is a list of the most recent ones:

Google Grant (2012--2013)
Text to Speech for Languages without an Orthography
PT-STAR (2009--2012)
Style-Specific Synthesis for Speech Translation
TRANSTAC (2010--2011)
Small-footprint Speech Synthesis under Android
GALE (2007--2009)
Syntax-Based Statistical Machine Translation (Chinese, Arabic — English)

Top words in my publications

Word List