activity
20182022
most citedRelative Positional Encoding for Speech Recognition and Direct Translation

1 citations · 2 across the 3 of their papers we have counts for

collaborators

11 papers

cs.CL2022

Adaptive multilingual speech recognition with pretrained models

Ngoc-Quan Pham, Alex Waibel, Jan Niehues

Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research. With the development of pretraining methods on audio and text d…

cs.CL2021

Efficient Weight factorization for Multilingual Speech Recognition

Ngoc-Quan Pham, Tuan-Nam Nguyen, Sebastian Stueker +1

End-to-end multilingual speech recognition involves using a single model training on a compositional speech corpus including many languages, resulting in a single neural network to…

cs.CL20211 cited

Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddings

Carlos Mullov, Ngoc-Quan Pham, Alexander Waibel

In this work we look into adding a new language to a multilingual NMT system in an unsupervised fashion. Under the utilization of pre-trained cross-lingual word embeddings we seek…

eess.AS20201 cited

Relative Positional Encoding for Speech Recognition and Direct Translation

Ngoc-Quan Pham, Thanh-Le Ha, Tuan-Nam Nguyen +5

Transformer models are powerful sequence-to-sequence architectures that are capable of directly mapping speech inputs to transcriptions or translations. However, the mechanism for…

eess.AS2020

High Performance Sequence-to-Sequence Model for Streaming Speech Recognition

Thai-Son Nguyen, Ngoc-Quan Pham, Sebastian Stueker +1

Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the c…

cs.CL2019

Modeling Confidence in Sequence-to-Sequence Models

Jan Niehues, Ngoc-Quan Pham

Recently, significant improvements have been achieved in various natural language processing tasks using neural sequence-to-sequence models. While aiming for the best generation qu…