We are pleased to inform you that the SYSPIN Text-to-Speech (TTS) models have been successfully uploaded to the BHASHINI platform, making them available for integration by end users and accessible to citizens via the Anuvaad web service and the BHASHINI Mobile Application. This marks a significant step toward enabling inclusive language technologies across India. Special thanks to Pranav and Amartyaveer for their dedicated efforts in making this release possible.
We are thrilled to announce that four papers from SPIRE Lab have been accepted for publication in the proceedings of InterSpeech 2025, to be held at Rotterdam, Netherlands. We are excited to share our research findings with the community and engage in meaningful discussions.
Read moreWe are excited to share that the research work of Veerababu Dharanalakota and Prasanta Kumar Ghosh on Physics-Informed Neural Networks for Acoustics is featured in Noise News International (NNI) Magazine! We are honored to be recognized and thank NNI for the opportunity to share our research.
Read moreContributing to the Open Day demos was an amazing experience!!
My most memorable experience was when we were pulling all-nighters to submit the Interspeech 2017 paper before the deadline.
Team Snacks after Friday Lab Talk was a lot of fun !!
SP Cup 2015 and SP Cup 2016 were some of my most fun projects ever.
I had a lot of fun working on cutting-edge speech recognition projects. This has tremendously helped me in finding jobs.
The internship was a huge learning experience both in terms of research as well as many other useful skills that helped me grow as an individual. Prasanta Sir has always been a great teacher and mentor.
It has been a great experience working with people at Spire Lab, I got to meet many new people who were very supportive and helpful.