Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Ngoc Thang Vu

Ngoc Thang Vu

ADVISER: A Toolkit for Developing Multi-modal, Multi-domain and Socially-engaged Conversational Agents

May 04, 2020
Chia-Yu Li, Daniel Ortega, Dirk Väth, Florian Lux, Lindsey Vanderlyn, Maximilian Schmidt, Michael Neumann, Moritz Völkel, Pavel Denisov, Sabrina Jenne, Zorica Kacarevic, Ngoc Thang Vu

Figure 1 for ADVISER: A Toolkit for Developing Multi-modal, Multi-domain and Socially-engaged Conversational Agents

Figure 2 for ADVISER: A Toolkit for Developing Multi-modal, Multi-domain and Socially-engaged Conversational Agents

* All authors contributed equally. Accepted to be presented at ACL - System demonstrations - 2020

Access Paper or Ask Questions

Code-switching Language Modeling With Bilingual Word Embeddings: A Case Study for Egyptian Arabic-English

Sep 24, 2019
Injy Hamed, Moritz Zhu, Mohamed Elmahdy, Slim Abdennadher, Ngoc Thang Vu

Figure 1 for Code-switching Language Modeling With Bilingual Word Embeddings: A Case Study for Egyptian Arabic-English

Figure 2 for Code-switching Language Modeling With Bilingual Word Embeddings: A Case Study for Egyptian Arabic-English

* Proceedings of the 21st International Conference on Speech and Computer (SPECOM'19), Istanbul, Turkey, August 20-25, 2019 https://link.springer.com/book/10.1007/978-3-030-26061-3
* 11 pages, 1 figure (having 2 sub-figures), submitted to the 21st International Conference on Speech and Computer (SPECOM'19),

Access Paper or Ask Questions

IMS-Speech: A Speech to Text Tool

Aug 13, 2019
Pavel Denisov, Ngoc Thang Vu

Figure 1 for IMS-Speech: A Speech to Text Tool

Figure 2 for IMS-Speech: A Speech to Text Tool

Figure 3 for IMS-Speech: A Speech to Text Tool

Figure 4 for IMS-Speech: A Speech to Text Tool

* ESSV 2019

Access Paper or Ask Questions

End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning

Aug 13, 2019
Pavel Denisov, Ngoc Thang Vu

Figure 1 for End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning

Figure 2 for End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning

Figure 3 for End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning

Figure 4 for End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning

* Interspeech 2019

Access Paper or Ask Questions

Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions

Feb 28, 2019
Daniel Ortega, Chia-Yu Li, Gisela Vallejo, Pavel Denisov, Ngoc Thang Vu

Figure 1 for Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions

Figure 2 for Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions

Figure 3 for Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions

Figure 4 for Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions

* 5 pages, 1 figure, ICASSP 2019, dialog act classification, automatic speech recognition

Access Paper or Ask Questions

Sequence-to-Sequence Models for Data-to-Text Natural Language Generation: Word- vs. Character-based Processing and Output Diversity

Oct 11, 2018
Glorianna Jagfeld, Sabrina Jenne, Ngoc Thang Vu

Figure 1 for Sequence-to-Sequence Models for Data-to-Text Natural Language Generation: Word- vs. Character-based Processing and Output Diversity

Figure 2 for Sequence-to-Sequence Models for Data-to-Text Natural Language Generation: Word- vs. Character-based Processing and Output Diversity

Figure 3 for Sequence-to-Sequence Models for Data-to-Text Natural Language Generation: Word- vs. Character-based Processing and Output Diversity

Figure 4 for Sequence-to-Sequence Models for Data-to-Text Natural Language Generation: Word- vs. Character-based Processing and Output Diversity

* INLG 2018

Access Paper or Ask Questions

Densely Connected Convolutional Networks for Speech Recognition

Aug 10, 2018
Chia Yu Li, Ngoc Thang Vu

Figure 1 for Densely Connected Convolutional Networks for Speech Recognition

Figure 2 for Densely Connected Convolutional Networks for Speech Recognition

Figure 3 for Densely Connected Convolutional Networks for Speech Recognition

Figure 4 for Densely Connected Convolutional Networks for Speech Recognition

* 5 pages, 3 figures, the 13th ITG conference on Speech Communication

Access Paper or Ask Questions

Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition

Jul 30, 2018
Pavel Denisov, Ngoc Thang Vu, Marc Ferras Font

Figure 1 for Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition

Figure 2 for Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition

Figure 3 for Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition

Figure 4 for Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition

* 5 pages, 2 figures, the 13th ITG conference on Speech Communication

Access Paper or Ask Questions

Low-Resource Text Classification using Domain-Adversarial Learning

Jul 13, 2018
Daniel Grießhaber, Ngoc Thang Vu, Johannes Maucher

Figure 1 for Low-Resource Text Classification using Domain-Adversarial Learning

Figure 2 for Low-Resource Text Classification using Domain-Adversarial Learning

Figure 3 for Low-Resource Text Classification using Domain-Adversarial Learning

* To be published on the 6th International Conference on Statistical Language and Speech Processing (SLSP) 2018

Access Paper or Ask Questions