|
sgondala@gatech.edu I'm a Research Engineer at Apple, where I build Language Models for Speech Recognition. I spend most of my time on various aspects of language modeling such as data selection, modeling architecture, scaling the training, and evaluating various approaches to improve Word Error Rate. Before this, I was a Master's student in Computer Science (Specializing in Machine Learning) at Georgia Tech at Prof. Devi Parikh's lab where I worked on problems in Language Grounding such as Image Captioning, Vision and Language Navigation. In a past life, I heavily worked on Systems. I was a Senior Software Developer at Oracle, where I worked on areas such as profiling, caching, and optimizing low-level mechanisms of a C++ query engine. I earned a Bachelor's degree in Computer Science in 2016 from IIT Bombay. In my spare time I enjoy reading books, cooking, and travel. |
|
|
|
|
Sashank Gondala*, Lyan Verwimp*, Ernest Pusateri, Manos Tsagkias, Christophe Van Gysel. Keywords: ASR, Language Model Pruning, discriminative, data selection, error prediction. Work done as a Research Intern at Apple. Published at ICASSP 2021 |
|
|
|
Sashank Gondala, Rachel Zhong, Harsh Agarwal. Worked on the idea of test-time training to improve performance of image captioning models on novel images. Incorporated several metrics that estimate the accuracy and fluency of captions without using paired data. Using these metrics as rewards, trained captioning models to optimize for them using PPO. |
|
Work under progress Building models to better solve the task of Vision & Language Navigation in Continuous Environment. |
|
|
|
Worked on an idea to provide decentralized CDN services by sharing the spare bandwidth and hard drive space of Internet users over blockchain. IP developed include a prototype to support HLS video streams and a whitepaper that describes the challenges and solutions including Service Certificates, Probabilistic Micropayments, etc. |
|
|
|
|
|