Mousmita Sarma
Speech Research Engineer at GoVivace Inc.
Hyderabad, Telangana, India
Summary
👤
Senior🎓
Top SchoolMousmita Sarma is a Speech Research Engineer and managing director with nine years of hands-on experience building ASR, voice biometrics and para-linguistic systems across English, multiple European languages and a wide range of Indian languages and dialects. She leads product-oriented research at GoVivace—shipping conversational voice bots and speech analytics—while also guiding the company’s technical and marketing strategy. Her work spans end-to-end engine development, speaker identification/verification, and extraction of speaker traits such as age, gender, emotion and accent, with practical deployments that prioritize inclusivity for India’s linguistic diversity. Mousmita blends academic rigor (PhD-level work on deep learning for speech) with pragmatic engineering, contributing to open-source tooling like Lhotse for speech data preparation. Known for turning research prototypes into production-ready engines, she uniquely combines leadership, product focus, and deep domain expertise in speech technologies.
9 years of coding experience
2 years of employment as a software developer
Bachelor of Science (B.Sc.), Electronics Science, Bachelor of Science (B.Sc.), Electronics Science at LCB College, GuwahatiHSLC, HSLC at Birjhora Girl's High School, BongaigaonMaster of Technology (M.Tech), Signal Processing, Communication Technology, Soft Computing, Master of Technology (M.Tech), Signal Processing, Communication Technology, Soft Computing at Department of Electronics and Communication Engineering, Gauhati UniversityDoctor of Philosophy (Ph.D.), Deep Learning Models and Optimization for Speech Based Applications, Doctor of Philosophy (Ph.D.), Deep Learning Models and Optimization for Speech Based Applications at Gauhati UniversityMaster of Science (M.Sc.), Electronics and Communication Technology, Master of Science (M.Sc.), Electronics and Communication Technology at Department of Electronics and Communication Technology, Gauhati University
English, Hindi, Assamese
Github Skills (12)
audio10
pytorch10
machine-learning10
speech10
python10
data-model10
user-data10
data-set10
data-processing10
deep-learning8
kaldi8
deeplearning-ai8
Programming languages (3)
Github contributions (5)
lhotse-speech/lhotse
Apr 2022 - May 2022
Tools for handling speech data in machine learning projects.
Role in this project:
ML Engineer
ML EngineerContributions:1 review, 5 commits, 4 comments in 15 days
Contributions summary:Mousmita contributed to the development of recipes for preparing speech data, specifically for the Eval2000 corpus. Their work involved creating Python scripts to process and structure audio and transcript data, generating recording and supervision manifests. They also refactored the code to incorporate data descriptions and removed unnecessary options.
pytorchkaldipythondatamachine-learning-projects
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.