Welcome to Bhaasha

Active Projects

Indic Language TTS

India is a country where several languages are spoken by over a billion people. Text-to-Speech systems for such languages will be extremely beneficial for wide-spread content creation and accessibility. This Demo will provide a clear idea on how an Indic TTS works in real time.

The languages available are Hindi, Telugu, and Malayalam. Select a language to listen to audio clips generated from pre-selected text samples. You can also select a custom text option to type in your own text and to generate audio for it. You will be able to enter the text in English and transliteration of the text will be done according to the chosen language. All demo options use our Indic TTS API to generate the Audio samples in real-time.

Audiobook

India is a country where several languages are spoken by over a billion people. Text-to-Speech systems for such languages will be extremely beneficial for wide-spread content creation and accessibility. This Demo will provide a clear idea on how an Indic TTS works in real time.

Information access from Document Images of Indian Languages

India is a country where several languages are spoken by over a billion people. Text-to-Speech systems for such languages will be extremely beneficial for wide-spread content creation and accessibility. This Demo will provide a clear idea on how an Indic TTS works in real time.

We focus on the content aware image processing algorithms for robust and efficient recognition and retrieval from Indian language document images. Our image processing algorithms aim at improving the quality of document images by removing the noise and low resolution artifacts by adopting content aware operations. We also work on developing recognizers using state of the art machine learning techniques such as deep learning for handwritten Indian language text. ‚ÄčIn this project, we specifically work on

Indian Language Benchmark System (ILBS)

India is a country where several languages are spoken by over a billion people. Text-to-Speech systems for such languages will be extremely beneficial for wide-spread content creation and accessibility. This Demo will provide a clear idea on how an Indic TTS works in real time.

LipSync

we aim to lip-sync unconstrained videos in the wild to any desired target speech. Current works excel at producing accurate lip movements on a static image or videos of specific people seen during the training phase. However, they fail to accurately morph the lip movements of arbitrary identities in dynamic, unconstrained talking face videos, resulting in significant parts of the video being out-of-sync with the new audio. We identify key reasons pertaining to this and resolve them by learning from a powerful lip-sync discriminator. Extensive quantitative evaluations on our challenging benchmarks show that the lip-sync accuracy of the videos generated by our Wav2Lip model is almost as good as real synced videos.

IL - Neural Machine Translation

----

NDL Search Engine

----