Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children's Speech

no code implementations • 13 Mar 2022 • Vishwanath Pratap Singh, Hardik Sailor, Supratik Bhattacharya, Abhishek Pandey

Then, this modified adult spectrum is used as augmented data to improve end-to-end ASR systems for children's speech recognition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

The Two Shades of Dubbing in Neural Machine Translation

no code implementations • COLING 2020 • Alina Karakanta, Supratik Bhattacharya, Shravan Nayak, Timo Baumann, Matteo Negri, Marco Turchi

Dubbing has two shades; synchronisation constraints are applied only when the actor{'}s mouth is visible on screen, while the translation is unconstrained for off-screen dubbing.

Machine Translation Translation +1