Direct Text to Speech Translation System using Acoustic Units

no code implementations • 14 Sep 2023 • Victoria Mingote, Pablo Gimeno, Luis Vicente, Sameer Khurana, Antoine Laurent, Jarod Duret

This framework employs text in different source languages as input to generate speech in the target language without the need for text transcriptions in this language.

Speech-to-Speech Translation text-to-speech translation +1

Improved Cross-Lingual Transfer Learning For Automatic Speech Translation

no code implementations • 1 Jun 2023 • Sameer Khurana, Nauman Dawalatabad, Antoine Laurent, Luis Vicente, Pablo Gimeno, Victoria Mingote, James Glass

Having a single model that supports multiple translation tasks is desirable.

Cross-Lingual Transfer Knowledge Distillation +4

Deep Speech Enhancement for Reverberated and Noisy Signals using Wide Residual Networks

no code implementations • 3 Jan 2019 • Dayana Ribas, Jorge Llombart, Antonio Miguel, Luis Vicente

The DNN model, trained with artificial synthesized reverberation data, was able to deal with far-field reverberated speech from real scenarios.

Speech Enhancement speech-recognition +1