Srija Anand

MS Student • IIT MadrasAI4Bharat

Hi! Thanks for visiting.

I am a first year MS Student at IIT Madras & AI4Bharat, where I'm advised by Mitesh M. Khapra.

Currently, my research interests align towards Text to Speech Synthesis (TTS).I work on building natural-sounding speech for the Indic languages with support for multiple voices, emotions and prosodic variations. My interest in Speech stems from the Speech Synthesis course taught by Prof. Pravesh Biyani at IIIT Delhi, back in 2020. My work on improving pronunciations in TTS systems IndicOOV recently got accepted at INTERSPEECH 2024. Previously, I was a software engineer at Microsoft where I worked on Data Protecion Manager.

Feel free to check out my resume and you can reach out to me via email

news

Sep, 2024 I'll be at NeurIPS 2024 (Vancouver) to present our work IndicVoices-R. If you're reading this, I'd love to chat, feel free to reach out via email or LinkedIn DM.
Sep, 2024 Our work IndicVoices-R got accepted at NeurIPS 2024 (Datasets and Benchmark). Yayyy! This unlocks 1.7k hours of TTS data in all 22 official Indian languages, covering more than 10k speakers.
Aug, 2024 Attending INTERSPEECH 2024, Greece to present IndicOOV. Let's catch up if you're there.
July, 2024 Started MS-Research at IIT Madras
June, 2024 Received the Young Female Researchers in Speech Workshop Travel Grant to attend INTERSPEECH 2024. Grateful!
June, 2024 Our paper IndicOOV got accepted at Interspeech 2024 :sparkles:

publications

  1. Interspeech 2024
    IndicOOV:Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies
    Srija Anand, SV Praveen, Ashwin Sankar, Mitesh M. Khapra
  2. NeurIPS-D&B'24
    IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS
    Ashwin Sankar†, Srija Anand†, Praveen Srinivasa Varadhan†, Sherry Thomas, Mehak Singal, Shridhar Kumar, Deovrat Mehendale, Aditi Krishana, Giri Raju, Mitesh Khapra