Vittorio Perera

I am a member of technical staff at Tenyx where I work on everything pertaining to NLP (from NLU to NLG to synthetic data generation) with the ambitious goal of building the next generation of intelligent voice-based agents.

Previously, I worked as applied scientist at Amazon Lab 126 in the Alexa Conversations group. During my tenure at Amazon I focused on controllable–both semantically and stylistically–natural language generation (NLG) at scale.

I earned my Ph.D. at Carnegie Mellon University working with Prof. Manuela Veloso. My thesis explored how to enable bidirectional human-robot interaction. In the human-to-robot direction, I developed algorithms to let a mobile service robot understand requests to perform tasks, and questions about its experience. In the robot-to-human direction, I enabled the robot to provide explanations about the task it executed with a level of detail that matches the user’s request.

Prior to CMU, I was a master student in Artificial Intelligence and Robotics at Sapienza University in Rome where I also got my B.S. in Computer Engeneering.

news

Jul 09, 2025	Pardon the dust! I’m currently moving the website from Bluehost to GitHub Pages and taking the opportunity to give it a little makeover. Over the next few days, some pages may still show content from the original template—thanks for your patience!
Oct 01, 2024	It’s official — Tenyx has been acquired by Salesforce! I’m incredibly excited about this milestone and what it means for our future. I’m looking forward to building voice agents with the power and scale of a company like Salesforce behind us!
May 27, 2024	Attending Contact Center Week in Las Vegas? Come find me at the Tenyx booth! I’ll be there all week—ask me about the voice agents we’re building. I’d love to chat!

selected publications

INLG

Schema-Guided Natural Language Generation

Yuheng Du, Shereen Oraby, Vittorio Perera, and 5 more authors

In Proceedings of the 13th International Conference on Natural Language Generation, 2020

Bib

@inproceedings{du-etal-2020-schema,
  title = {Schema-Guided Natural Language Generation},
  author = {Du, Yuheng and Oraby, Shereen and Perera, Vittorio and Shen, Minmin and Narayan-Chen, Anjali and Chung, Tagyoung and Venkatesh, Anushree and Hakkani-Tur, Dilek},
  booktitle = {Proceedings of the 13th International Conference on Natural Language Generation},
  year = {2020},
  publisher = {Association for Computational Linguistics},
}

AAAI

Multi-Task Learning for Parsing the Alexa Meaning Representation Language

Vittorio Perera, Tagyoung Chung, Thomas Kollar, and 1 more author

In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), 2018

Bib

@inproceedings{perera2018multi,
  title = {Multi-Task Learning for Parsing the Alexa Meaning Representation Language},
  author = {Perera, Vittorio and Chung, Tagyoung and Kollar, Thomas and Strubell, Emma},
  booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence, (AAAI-18)},
  year = {2018},
  publisher = {{AAAI} Press},
}

Robotics

Learning Task Knowledge from Dialog and Web Access

Vittorio Perera, Robin Soetens, Thomas Kollar, and 5 more authors

Robotics, 2015

Bib

@article{perera2015learning,
  title = {Learning Task Knowledge from Dialog and Web Access},
  author = {Perera, Vittorio and Soetens, Robin and Kollar, Thomas and Samadi, Mehdi and Sun, Yichao and Nardi, Daniele and van de Molengraft, Ren{\'e} and Veloso, Manuela},
  journal = {Robotics},
  year = {2015},
  publisher = {Multidisciplinary Digital Publishing Institute},
}