Replacing Human Audio with Synthetic Audio for On-device Unspoken Punctuation Prediction

no code implementations • 20 Oct 2020 • Daria Soboleva, Ondrej Skopek, Márius Šajgalík, Victor Cărbune, Felix Weissenberger, Julia Proskurnia, Bogdan Prisacari, Daniel Valcarce, Justin Lu, Rohit Prabhavalkar, Balint Miklos

We present a novel multi-modal unspoken punctuation prediction system for the English language which combines acoustic and text features.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Insertion-Deletion Transformer

no code implementations • 15 Jan 2020 • Laura Ruis, Mitchell Stern, Julia Proskurnia, William Chan

We propose the Insertion-Deletion Transformer, a novel transformer-based neural architecture and training method for sequence generation.

Translation