Welcome to my homepage!

Namaskara! I'm a Post Doc Researcher at Microsoft Research India in Bangalore, India, where I work on Speech Processing for Multilingual Communities. Currently, the focus of my work is on building Deep-learning based Acoustic and Language Models that can handle code-switching without needing a large amount of code-switched training data. At MSRI, I am part of Project Melange in which we look at various aspects of code-switching and mixing, including how and why multilinguals code-switch. We recently organized a Special Session at Interspeech 2017 on Speech Technologies for Code-switching. I also maintain the Project Melange blog, Poco Mix Maadi, where our group and others regularly post articles related to multilingualism and code-mixing.

Previously, I was a PhD student in the Language Technologies Institute, Carnegie Mellon University. I worked on Text-to-Speech systems with my advisor Alan W Black, and my thesis was on pronunciation modeling for low-resource languages.

I am currently on the job market and am looking for positions in Bangalore starting January 2018. If you know of an interesting opening in Speech, NLP or Machine Learning, please get in touch!

Publications

Conference, workshop and journal papers

  • 'Speech Synthesis for Mixed-Language Navigation Instructions', Khythiraghavi Chandu, Sai Krishna Rallabandi, Sunayana Sitaram, Alan W Black, Interspeech 2017, Stockholm, Sweden.
  • 'Experiments with Cross-lingual Systems for Synthesis of Code-Mixed Text', Sunayana Sitaram, Sai Krishna Rallabandi, Shruti Rijhwani, Alan W Black, Speech Synthesis Workshop 9 (2016), Sunnyvale, USA.
  • 'Open-Source Consumer-Grade Indic Text To Speech', Andrew Wilkinson, Alok Parlikar, Sunayana Sitaram, Tim White, Alan W Black, Suresh Bazaj, Speech Synthesis Workshop 9 (2016), Sunnyvale, USA.
  • 'The Indic Frontend for Grapheme to Phoneme Conversion', Alok Parlikar, Sunayana Sitaram, Andrew Wilkinson and Alan W Black, in Proceedings of the 3rd Workshop on Indian Language Data: Resources and Evaluation 2016, Portoroz, Slovenia.
  • 'Polyglot Neural Language Models: Case Study in Cross-Lingual Phonetic Representation Learning', Yulia Tsvetkov, Sunayana Sitaram, Manaal Faruqui, Guillaume Lample, Patrick Littell, David Mortensen, Alan W Black, Lori Levin and Chris Dyer. Proc. NAACL'16.
  • 'Speech Synthesis of Code Mixed Text', Sunayana Sitaram and Alan W Black, LREC 2016, Portoroz, Slovenia.
  • 'Universal Grapheme-based Speech Synthesis', Sunayana Sitaram, Alok Parlikar, Gopala Krishna Anumanchipalli and Alan W Black, Interspeech 2015, Dresden, Germany.
  • 'Using Acoustics to Improve Pronunciation for Synthesis of Low Resource Languages', Sunayana Sitaram, Serena Jeblee and Alan W Black, Interspeech 2015, Dresden, Germany.
  • 'Using Articulatory Features and Inferred Phonological Segments in Zero Resource Speech Processing', Pallavi Baljekar, Sunayana Sitaram, Prasannakumar Muthukumar and Alan W Black, Interspeech 2015, Dresden, Germany.
  • 'Text to Speech in New Languages without a Standardized Orthography', Sunayana Sitaram , Gopala Anumanchipalli, Justin Chiu, Alok Parlikar and Alan W Black, SSW 8 (2013), Barcelona, Spain.
  • 'Bootstrapping Text-to-Speech for Speech Processing in Languages without an Orthography', Sunayana Sitaram, Sukhada Palkar, Yun-Nung Chen, Alok Parlikar and Alan W Black, ICASSP (2013), Vancouver, Canada
  • 'A Hindi Speech Recognizer for an Agricultural Video Search Application', Kalika Bali, Sunayana Sitaram, Sebastien Cuendet, and Indrani Medhi, ACM Symposium on Computing for Development (ACM DEV), January 2013
  • ''Mining data from Project LISTEN's Reading Tutor to analyze development of children's oral reading prosody', Sunayana Sitaram, Jack Mostow, FLAIRS 2012, Florida, Best Paper Award.
  • 'What visual feedback should a reading tutor give children on their oral reading prosody?', Sunayana Sitaram, Jack Mostow, Yuanpeng Li, Anders Weinstein, David Yen, Joe Valeri, SLaTe, August 2011, Venice, Italy.
  • 'Mining data from Project LISTEN's Reading Tutor to analyze development of children's oral reading prosody', Jack Mostow, Sunayana Sitaram, Society of Scientific Study of Reading, Florida, July 2011.
  • 'Two Methods for Assessing Oral Reading Prosody', Minh Duong, Jack Mostow, Sunayana Sitaram, ACM Transactions on Speech and Language Processing (Special Issue on Speech and Language Processing of Children's Speech for Child-machine Interaction Applications), 7(4): 14:11-22.
  • 'DA-IICT Cross Lingual and Multilingual Corpora for Speaker Recognition', Hemant Patil, Sunayana Sitaram, Esha Sharma, Proceedings of the International Conference on Advances in Pattern Recognition ICAPR-09, Kolkata, India, IEEE Computer Society.

Other publications and talks

  • 'HospitalLine: A Spoken Dialog System for Hospitals', Sunayana Sitaram, technical poster at Grace Hopper Celebration for Women in Computing 2008, Colorado in October 2008.
  • 'Font recognition for Indian Language Document Viewing', Sunayana Sitaram, Opportunities for Undergraduate Research in Computer Science, Carnegie Mellon University, USA in October, 2007.
  • 'Student Groups Networking + Integrating Ideas = Together We Can Make a Better World', Alicia Chong, Sunayana Sitaram, Aakriti Agarwal and Kate Tsoukalas, BOF session, Grace Hopper Celebration of Women in Computing 2008, Colorado, October 2008.
  • 'Speech @ CMU and Project Listen', invited talk, DAIICT, India in May 2011
  • 'Text to Speech Systems', invited talk, DAIICT, India in June 2012
  • 'TTS without text', invited talk, DAIICT, India in Jan 2014
  • 'TTS for languages with ambiguous written forms', invited talk, DAIICT Workshop on Text to Speech Synthesis, India in June 2014

Other Stuff

Coming soon!

Office: Microsoft Research India,

#9, Vigyan, Lavelle Road, Bangalore

Email: t-susita atmicrosoftdotcom