no code implementations • 27 Jan 2021 • Debarati B. Chakraborty, Mukesh Sharma, Bhaskar Vijay
Both the proposed methods are validated with off-line as well as with on-line video datasets in real-time.
no code implementations • 20 Apr 2020 • Abhishek Niranjan, Mukesh Sharma, Sai Bharath Chandra Gutha, M Ali Basha Shaik
We introduce whisper-to-natural-speech conversion using sequence-to-sequence approach by proposing enhanced transformer architecture, which uses both parallel and non-parallel data.