Publications de Sibo Tong | EPFL Graph Search

A Bayesian Approach to Recurrence in Neural Networks

2021

Lattice-Free Maximum Mutual Information Training of Multilingual Speech Recognition System

Hervé Bourlard, Petr Motlicek, Sibo Tong

ISCA2020

Multilingual Training and Adaptation in Speech Recognition

State-of-the-art acoustic models for Automatic Speech Recognition (ASR) are based on Hidden Markov Models (HMM) and Deep Neural Networks (DNN) and often require thousands of hours of transcribed speech data during training. Therefore, building multilingual ...

EPFL2020

Cross-lingual Adaptation of a CTC-based multilingual Acoustic Model

Hervé Bourlard, Philip Neil Garner, Sibo Tong

Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages. However, initialisation from monolingual context-de ...

ELSEVIER SCIENCE BV2018

Fast Language Adaptation Using Phonological Information

Hervé Bourlard, Sibo Tong, Philip Neil Garner

Phoneme-based multilingual connectionist temporal classification (CTC) model is easily extensible to a new language by concatenating parameters of the new phonemes to the output layer. In the present paper, we improve cross-lingual adaptation in the contex ...

ISCA-INT SPEECH COMMUNICATION ASSOC2018

The SUMMA Platform Prototype

Hervé Bourlard, Andrei Popescu-Belis, Philip Neil Garner, Nikolaos Pappas, Sibo Tong, Yang Wang, Ahmed Ali, Steve Renals, Lesly Sadiht Miculicich Werlen, Marco Damonte

We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring. The platform contains a rich suite of low-level and high-level natural language processing technologies: automatic speech recognition of broadca ...

Association for Computational Linguistics2017