default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDNgoc Thang Vu
Person information
- affiliation: University of Stuttgart, Institute for Natural Language Processing, Germany
- affiliation: University of Munich, Center for Information and Language Processing, Germany
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[c134]Wei Zhou
, Heike Adel, Hendrik Schuff, Ngoc Thang Vu:
Explaining Pre-Trained Language Models with Attribution Scores: An Analysis in Low-Resource Settings. LREC/COLING 2024: 6867-6875- [c133]Pascal Tilli, Ngoc Thang Vu:
Intrinsic Subgraph Generation for Interpretable Graph Based Visual Question Answering. LREC/COLING 2024: 9204-9223 - [c132]Maximilian Schmidt, Andrea Bartezzaghi, Ngoc Thang Vu:
Prompting-based Synthetic Data Generation for Few-Shot Question Answering. LREC/COLING 2024: 13168-13178 - [c131]Dirk Väth, Lindsey Vanderlyn, Ngoc Thang Vu:
Towards a Zero-Data, Controllable, Adaptive Dialog System. LREC/COLING 2024: 16433-16449 - [c130]Maximilian Kimmich, Andrea Bartezzaghi, Jasmina Bogojeska, Cristiano Malossi, Ngoc Thang Vu:
Combining Data Generation and Active Learning for Low-Resource Question Answering. ICANN (7) 2024: 131-147 - [c129]Daniel Ortega, Steven Söhnel, Ngoc Thang Vu:
Improving and Understanding Clarifying Question Generation in Conversational Search. TSD (2) 2024: 222-235 - [i89]Wei Zhou, Heike Adel, Hendrik Schuff, Ngoc Thang Vu:
Explaining Pre-Trained Language Models with Attribution Scores: An Analysis in Low-Resource Settings. CoRR abs/2403.05338 (2024) - [i88]Dirk Väth, Lindsey Vanderlyn, Ngoc Thang Vu:
Towards a Zero-Data, Controllable, Adaptive Dialog System. CoRR abs/2403.17582 (2024) - [i87]Pascal Tilli, Ngoc Thang Vu:
Intrinsic Subgraph Generation for Interpretable Graph based Visual Question Answering. CoRR abs/2403.17647 (2024) - [i86]Pavel Denisov, Ngoc Thang Vu:
Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training. CoRR abs/2404.10922 (2024) - [i85]Maximilian Schmidt, Andrea Bartezzaghi, Ngoc Thang Vu:
Prompting-based Synthetic Data Generation for Few-Shot Question Answering. CoRR abs/2405.09335 (2024) - [i84]Florian Lux, Sarina Meyer, Lyonel Behringer, Frank Zalkow, Phat Do, Matt Coler, Emanuël A. P. Habets, Ngoc Thang Vu:
Meta Learning Text-to-Speech Synthesis in over 7000 Languages. CoRR abs/2406.06403 (2024) - [i83]Thomas Bott, Florian Lux, Ngoc Thang Vu:
Controlling Emotion in Text-to-Speech with Natural Language Prompts. CoRR abs/2406.06406 (2024) - [i82]Sarina Meyer, Florian Lux, Ngoc Thang Vu:
Probing the Feasibility of Multilingual Speaker Anonymization. CoRR abs/2407.02937 (2024) - [i81]Chia-Yu Li, Ngoc Thang Vu:
Improving noisy student training for low-resource languages in End-to-End ASR using CycleGAN and inter-domain losses. CoRR abs/2407.21061 (2024) - [i80]Lucas Möller, Pascal Tilli, Ngoc Thang Vu, Sebastian Padó:
Explaining Vision-Language Similarities in Dual Encoders with Feature-Pair Attributions. CoRR abs/2408.14153 (2024) - [i79]Lindsey Vanderlyn, Dirk Väth, Ngoc Thang Vu:
Investigating the effect of Mental Models in User Interaction with an Adaptive Dialog Agent. CoRR abs/2408.14154 (2024) - [i78]Tushar Dhyani, Florian Lux, Michele Mancusi, Giorgio Fabbro, Fritz Hohl, Ngoc Thang Vu:
High-Resolution Speech Restoration with Latent Diffusion Model. CoRR abs/2409.11145 (2024) - [i77]Dirk Väth, Ngoc Thang Vu:
A Zero-Shot approach to the Conversational Tree Search Task. CoRR abs/2410.05821 (2024) - 2023
- [j9]Anton Batliner, Michael Neumann, Felix Burkhardt, Alice Baird, Sarina Meyer, Ngoc Thang Vu, Björn W. Schuller:
Ethical Awareness in Paralinguistics: A Taxonomy of Applications. Int. J. Hum. Comput. Interact. 39(9): 1904-1921 (2023) - [j8]Hendrik Schuff, Lindsey Vanderlyn, Heike Adel, Ngoc Thang Vu:
How to do human evaluation: A brief introduction to user studies in NLP. Nat. Lang. Eng. 29(5): 1199-1222 (2023) - [c128]Dirk Väth, Lindsey Vanderlyn, Ngoc Thang Vu:
DIAGRAPH: An Open-Source Graphic Interface for Dialog Flow Design. ACL (demo) 2023: 136-143 - [c127]Manuel Mager, Elisabeth Mager, Katharina Kann, Ngoc Thang Vu:
Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers. ACL (1) 2023: 4871-4897 - [c126]Alon Jacovi, Hendrik Schuff, Heike Adel, Ngoc Thang Vu, Yoav Goldberg:
Neighboring Words Affect Human Interpretation of Saliency Explanations. ACL (Findings) 2023: 11816-11833 - [c125]Pavel Denisov, Ngoc Thang Vu:
Leveraging Multilingual Self-Supervised Pretrained Models for Sequence-to-Sequence End-to-End Spoken Language Understanding. ASRU 2023: 1-8 - [c124]Florian Lux, Julia Koch, Sarina Meyer, Thomas Bott, Nadja Schauffler, Pavel Denisov, Antje Schweitzer, Ngoc Thang Vu:
The IMS Toucan System for the Blizzard Challenge 2023. Blizzard Challenge 2023 - [c123]Esra Dönmez, Pascal Tilli, Hsiu-Yu Yang, Ngoc Thang Vu, Carina Silberer:
HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities. CoNLL 2023: 364-388 - [c122]Dirk Väth, Lindsey Vanderlyn, Ngoc Thang Vu:
Conversational Tree Search: A New Hybrid Dialog Task. EACL 2023: 1256-1272 - [c121]Marwa Gaser, Manuel Mager, Injy Hamed, Nizar Habash, Slim Abdennadher, Ngoc Thang Vu:
Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text. EACL 2023: 3505-3520 - [c120]Sarina Meyer, Florian Lux, Julia Koch, Pavel Denisov, Pascal Tilli, Ngoc Thang Vu:
Prosody Is Not Identity: A Speaker Anonymization Approach Using Prosody Cloning. ICASSP 2023: 1-5 - [c119]Daniel Grießhaber, Johannes Maucher, Ngoc Thang Vu:
Regularisation for Efficient Softmax Parameter Generation in Low-Resource Text Classifiers. IJCAI 2023: 5058-5066 - [c118]Florian Lux, Pascal Tilli, Sarina Meyer, Ngoc Thang Vu:
Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directions. INTERSPEECH 2023: 4788-4792 - [c117]Noel Schäfer, Sebastian Künzel, Tanja Munz-Körner, Pascal Tilli, Sandeep Vidyapu, Ngoc Thang Vu, Daniel Weiskopf:
Visual Analysis of Scene-Graph-Based Visual Question Answering. VINCI 2023: 25:1-25:8 - [d5]Noel Schäfer, Pascal Tilli, Tanja Munz-Körner, Sebastian Künzel, Sandeep Vidyapu, Ngoc Thang Vu, Daniel Weiskopf:
Visual Analysis System for Scene-Graph-Based Visual Question Answering. DaRUS, 2023
- [d4]Noel Schäfer, Pascal Tilli, Tanja Munz-Körner, Sebastian Künzel, Sandeep Vidyapu, Ngoc Thang Vu, Daniel Weiskopf:
Model Parameters and Evaluation Data for our Visual Analysis System for Scene-Graph-Based Visual Question Answering. DaRUS, 2023 - [i76]Dirk Väth, Lindsey Vanderlyn, Ngoc Thang Vu:
Conversational Tree Search: A New Hybrid Dialog Task. CoRR abs/2303.10227 (2023) - [i75]Daniel Ortega, Sarina Meyer, Antje Schweitzer, Ngoc Thang Vu:
Modeling Speaker-Listener Interaction for Backchannel Prediction. CoRR abs/2304.04472 (2023) - [i74]Daniel Ortega, Chia-Yu Li, Ngoc Thang Vu:
Oh, Jeez! or Uh-huh? A Listener-aware Backchannel Predictor on ASR Transcriptions. CoRR abs/2304.04478 (2023) - [i73]Alon Jacovi, Hendrik Schuff, Heike Adel, Ngoc Thang Vu, Yoav Goldberg:
Neighboring Words Affect Human Interpretation of Saliency Explanations. CoRR abs/2305.02679 (2023) - [i72]Manuel Mager, Elisabeth Mager, Katharina Kann, Ngoc Thang Vu:
Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers. CoRR abs/2305.19474 (2023) - [i71]Manuel Mager, Rajat Bhatnagar, Graham Neubig, Ngoc Thang Vu, Katharina Kann:
Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction. CoRR abs/2306.06804 (2023) - [i70]Sarina Meyer, Xiaoxiao Miao, Ngoc Thang Vu:
VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research. CoRR abs/2309.08049 (2023) - [i69]Pavel Denisov, Ngoc Thang Vu:
Leveraging Multilingual Self-Supervised Pretrained Models for Sequence-to-Sequence End-to-End Spoken Language Understanding. CoRR abs/2310.06103 (2023) - [i68]Injy Hamed, Nizar Habash, Ngoc Thang Vu:
Data Augmentation Techniques for Machine Translation of Code-Switched Texts: A Comparative Study. CoRR abs/2310.15262 (2023) - [i67]Florian Lux, Julia Koch, Sarina Meyer, Thomas Bott, Nadja Schauffler, Pavel Denisov, Antje Schweitzer, Ngoc Thang Vu:
The IMS Toucan System for the Blizzard Challenge 2023. CoRR abs/2310.17499 (2023) - [i66]Florian Lux, Pascal Tilli, Sarina Meyer, Ngoc Thang Vu:
Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directions. CoRR abs/2310.17502 (2023) - 2022
- [j7]Tanja Munz, Dirk Väth, Paul Kuznecov, Ngoc Thang Vu, Daniel Weiskopf:
Visualization-based improvement of neural machine translation. Comput. Graph. 103: 45-60 (2022) - [j6]Injy Hamed, Pavel Denisov, Chia-Yu Li, Mohamed Elmahdy, Slim Abdennadher, Ngoc Thang Vu:
Investigations on speech recognition systems for low-resource dialectal Arabic-English code-switching speech. Comput. Speech Lang. 72: 101278 (2022) - [j5]Katharina Kann, Abteen Ebrahimi, Manuel Mager, Arturo Oncevay, John E. Ortega, Annette Rios, Angela Fan, Ximena Gutierrez-Vasques, Luis Chiruzzo, Gustavo Alberto Giménez Lugo, Ricardo Ramos, Iván Vladimir Meza Ruíz, Elisabeth Mager, Vishrav Chaudhary, Graham Neubig, Alexis Palmer, Rolando Coto-Solano, Ngoc Thang Vu:
AmericasNLI: Machine translation and natural language inference systems for Indigenous languages of the Americas. Frontiers Artif. Intell. 5 (2022) - [j4]Injy Hamed, Alia El Bolock, Cornelia Herbert, Slim Abdennadher, Ngoc Thang Vu:
The Who in Code-Switching: A Case Study for Predicting Egyptian Arabic-English Code-Switching Levels Based on Character Profiles. Int. J. Asian Lang. Process. 32(1): 2250010:1-2250010:22 (2022) - [c116]Manuel Mager, Arturo Oncevay, Elisabeth Mager, Katharina Kann, Ngoc Thang Vu:
BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages. ACL (Findings) 2022: 961-971 - [c115]Abteen Ebrahimi, Manuel Mager, Arturo Oncevay, Vishrav Chaudhary, Luis Chiruzzo, Angela Fan, John E. Ortega, Ricardo Ramos, Annette Rios, Iván Vladimir Meza Ruíz, Gustavo Giménez Lugo, Elisabeth Mager, Graham Neubig, Alexis Palmer, Rolando Coto-Solano, Ngoc Thang Vu, Katharina Kann:
AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages. ACL (1) 2022: 6279-6299 - [c114]Florian Lux, Ngoc Thang Vu:
Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features. ACL (1) 2022: 6858-6868 - [c113]Hendrik Schuff, Alon Jacovi, Heike Adel, Yoav Goldberg, Ngoc Thang Vu:
Human Interpretation of Saliency-based Explanation Over Text. FAccT 2022: 611-636 - [c112]Siddhant Arora, Siddharth Dalmia, Pavel Denisov, Xuankai Chang, Yushi Ueda, Yifan Peng, Yuekai Zhang, Sujay Kumar, Karthik Ganesan, Brian Yan, Ngoc Thang Vu, Alan W. Black, Shinji Watanabe:
ESPnet-SLU: Advancing Spoken Language Understanding Through ESPnet. ICASSP 2022: 7167-7171 - [c111]Lindsey Vanderlyn, Talita Anthonio, Daniel Ortega, Michael Roth, Ngoc Thang Vu:
Toward Implicit Reference in Dialog: A Survey of Methods and Data. AACL/IJCNLP (1) 2022: 587-600 - [c110]Florian Lux, Julia Koch, Ngoc Thang Vu:
Low-Resource Multilingual and Zero-Shot Multispeaker TTS. AACL/IJCNLP (1) 2022: 741-751 - [c109]Julia Koch, Florian Lux, Nadja Schauffler, Toni Bernhart, Felix Dieterle, Jonas Kuhn, Sandra Richter, Gabriel Viehhauser, Ngoc Thang Vu:
PoeticTTS - Controllable Poetry Reading for Literary Studies. INTERSPEECH 2022: 1223-1227 - [c108]Sarina Meyer, Florian Lux, Pavel Denisov, Julia Koch, Pascal Tilli, Ngoc Thang Vu:
Speaker Anonymization with Phonetic Intermediate Representations. INTERSPEECH 2022: 4925-4929 - [c107]Nadja Schauffler, Toni Bernhart, André Blessing, Gunilla Eschenbach, Markus Gärtner, Kerstin Jung, Anna Kinder, Julia Koch, Sandra Richter, Gabriel Viehhauser, Ngoc Thang Vu, Lorenz Wesemann, Jonas Kuhn:
»textklang« - Towards a Multi-Modal Exploration Platform for German Poetry. LREC 2022: 5345-5355 - [c106]Chia-Yu Li, Ngoc Thang Vu:
Improving Semi-Supervised End-To-End Automatic Speech Recognition Using Cyclegan and Inter-Domain Losses. SLT 2022: 822-829 - [c105]Florian Lux, Ching-Yi Chen, Ngoc Thang Vu:
Combining Contrastive and Non-Contrastive Losses for Fine-Tuning Pretrained Models in Speech Analysis. SLT 2022: 876-883 - [c104]Sarina Meyer, Pascal Tilli, Pavel Denisov, Florian Lux, Julia Koch, Ngoc Thang Vu:
Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy. SLT 2022: 912-919 - [c103]Florian Lux, Julia Koch, Ngoc Thang Vu:
Exact Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech. SLT 2022: 962-969 - [c102]Injy Hamed, Nizar Habash, Slim Abdennadher, Ngoc Thang Vu:
ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic-English. WANLP@EMNLP 2022: 119-130 - [d3]Tanja Munz, Dirk Väth, Paul Kuznecov, Ngoc Thang Vu, Daniel Weiskopf:
NMTVis - Extended Neural Machine Translation Visualization System. DaRUS, 2022 - [i65]Hendrik Schuff, Alon Jacovi, Heike Adel, Yoav Goldberg, Ngoc Thang Vu:
Human Interpretation of Saliency-based Explanation Over Text. CoRR abs/2201.11569 (2022) - [i64]Florian Lux, Ngoc Thang Vu:
Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features. CoRR abs/2203.03191 (2022) - [i63]Manuel Mager, Arturo Oncevay, Elisabeth Mager, Katharina Kann, Ngoc Thang Vu:
BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages. CoRR abs/2203.08954 (2022) - [i62]Hung-yi Lee, Shang-Wen Li, Ngoc Thang Vu:
Meta Learning for Natural Language Processing: A Survey. CoRR abs/2205.01500 (2022) - [i61]Injy Hamed, Nizar Habash, Slim Abdennadher, Ngoc Thang Vu:
Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation. CoRR abs/2205.12649 (2022) - [i60]Florian Lux, Julia Koch, Ngoc Thang Vu:
Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech. CoRR abs/2206.12229 (2022) - [i59]Sarina Meyer, Florian Lux, Pavel Denisov, Julia Koch, Pascal Tilli, Ngoc Thang Vu:
Speaker Anonymization with Phonetic Intermediate Representations. CoRR abs/2207.04834 (2022) - [i58]Julia Koch, Florian Lux, Nadja Schauffler, Toni Bernhart, Felix Dieterle, Jonas Kuhn, Sandra Richter, Gabriel Viehhauser, Ngoc Thang Vu:
PoeticTTS - Controllable Poetry Reading for Literary Studies. CoRR abs/2207.05549 (2022) - [i57]Injy Hamed, Alia El Bolock, Cornelia Herbert, Slim Abdennadher, Ngoc Thang Vu:
The Who in Code-Switching: A Case Study for Predicting Egyptian Arabic-English Code-Switching Levels based on Character Profiles. CoRR abs/2208.00433 (2022) - [i56]Marwa Gaser, Manuel Mager, Injy Hamed, Nizar Habash, Slim Abdennadher, Ngoc Thang Vu:
Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text. CoRR abs/2210.06990 (2022) - [i55]Sarina Meyer, Pascal Tilli, Pavel Denisov, Florian Lux, Julia Koch, Ngoc Thang Vu:
Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy. CoRR abs/2210.07002 (2022) - [i54]Hendrik Schuff, Heike Adel, Peng Qi, Ngoc Thang Vu:
How (Not) To Evaluate Explanation Quality. CoRR abs/2210.07126 (2022) - [i53]Chia-Yu Li, Ngoc Thang Vu:
Improving Semi-supervised End-to-end Automatic Speech Recognition using CycleGAN and Inter-domain Losses. CoRR abs/2210.11642 (2022) - [i52]Florian Lux, Julia Koch, Ngoc Thang Vu:
Low-Resource Multilingual and Zero-Shot Multispeaker TTS. CoRR abs/2210.12223 (2022) - [i51]Florian Lux, Ching-Yi Chen, Ngoc Thang Vu:
Combining Contrastive and Non-Contrastive Losses for Fine-Tuning Pretrained Models in Speech Analysis. CoRR abs/2211.01964 (2022) - [i50]Injy Hamed, Nizar Habash, Slim Abdennadher, Ngoc Thang Vu:
ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic - English. CoRR abs/2211.12000 (2022) - 2021
- [c101]Chia-Yu Li, Ngoc Thang Vu:
Improving Speech Recognition on Noisy Speech via Speech Enhancement with Multi-Discriminators CycleGAN. ASRU 2021: 830-836 - [c100]Hendrik Schuff, Hsiu-Yu Yang, Heike Adel, Ngoc Thang Vu:
Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings. BlackboxNLP@EMNLP 2021: 26-41 - [c99]Florian Lux, Julia Koch, Antje Schweitzer, Ngoc Thang Vu:
The IMS Toucan system for the Blizzard Challenge 2021. Blizzard Challenge 2021 - [c98]Katharina Weitz, Lindsey Vanderlyn, Ngoc Thang Vu, Elisabeth André:
"It's our fault!": Insights Into Users' Understanding and Interaction With an Explanatory Collaborative Dialog System. CoNLL 2021: 1-16 - [c97]Lindsey Vanderlyn, Gianna Weber, Michael Neumann, Dirk Väth, Sarina Meyer, Ngoc Thang Vu:
"It seemed like an annoying woman": On the Perception and Ethical Considerations of Affective Language in Text-Based Conversational Agents. CoNLL 2021: 44-57 - [c96]Cennet Oguz, Ngoc Thang Vu:
Few-shot Learning for Slot Tagging with Attentive Relational Network. EACL 2021: 1566-1572 - [c95]Dirk Väth, Pascal Tilli, Ngoc Thang Vu:
Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking. EMNLP (Demos) 2021: 114-123 - [c94]Tanja Munz, Dirk Väth, Paul Kuznecov, Ngoc Thang Vu, Daniel Weiskopf:
Visual-Interactive Neural Machine Translation. Graphics Interface 2021: 265-274 - [c93]Injy Hamed, Alia El Bolock, Nader Rizk, Cornelia Herbert, Slim Abdennadher, Ngoc Thang Vu:
Predicting User Code-Switching Level from Sociological and Psychological Profiles. IALP 2021: 395-400 - [c92]Florian Lux, Ngoc Thang Vu:
Meta-Learning for Improving Rare Word Recognition in End-to-End ASR. ICASSP 2021: 5974-5978 - [c91]Pavel Denisov, Manuel Mager, Ngoc Thang Vu:
IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task. IWSLT 2021: 175-181 - [c90]Michael Neumann, Ngoc Thang Vu:
Investigations on audiovisual emotion recognition in noisy conditions. SLT 2021: 358-364 - [d2]Tanja Munz, Dirk Väth, Paul Kuznecov, Ngoc Thang Vu, Daniel Weiskopf:
NMTVis - Neural Machine Translation Visualization System. DaRUS, 2021 - [d1]Tanja Munz, Dirk Väth, Paul Kuznecov, Ngoc Thang Vu, Daniel Weiskopf:
NMTVis - Trained Models for our Visual Analytics System. DaRUS, 2021 - [i49]Florian Lux, Ngoc Thang Vu:
Meta-Learning for improving rare word recognition in end-to-end ASR. CoRR abs/2102.12624 (2021) - [i48]Michael Neumann, Ngoc Thang Vu:
Investigations on Audiovisual Emotion Recognition in Noisy Conditions. CoRR abs/2103.01894 (2021) - [i47]Cennet Oguz, Ngoc Thang Vu:
Few-shot Learning for Slot Tagging with Attentive Relational Network. CoRR abs/2103.02333 (2021) - [i46]Abteen Ebrahimi, Manuel Mager, Arturo Oncevay, Vishrav Chaudhary, Luis Chiruzzo, Angela Fan, John E. Ortega, Ricardo Ramos, Annette Rios, Ivan Vladimir, Gustavo Alberto Giménez Lugo, Elisabeth Mager, Graham Neubig, Alexis Palmer, Rolando Coto-Solano, Ngoc Thang Vu, Katharina Kann:
AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages. CoRR abs/2104.08726 (2021) - [i45]Pavel Denisov, Manuel Mager, Ngoc Thang Vu:
IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task. CoRR abs/2106.16055 (2021) - [i44]Hendrik Schuff, Heike Adel, Ngoc Thang Vu:
Thought Flow Nets: From Single Predictions to Trains of Model Thought. CoRR abs/2107.12220 (2021) - [i43]Injy Hamed, Pavel Denisov, Chia-Yu Li, Mohamed Elmahdy, Slim Abdennadher, Ngoc Thang Vu:
Investigations on Speech Recognition Systems for Low-Resource Dialectal Arabic-English Code-Switching Speech. CoRR abs/2108.12881 (2021) - [i42]Hendrik Schuff, Hsiu-Yu Yang, Heike Adel, Ngoc Thang Vu:
Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings. CoRR abs/2109.07833 (2021) - [i41]Dirk Väth, Pascal Tilli, Ngoc Thang Vu:
Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking. CoRR abs/2110.05159 (2021) - [i40]Siddhant Arora, Siddharth Dalmia, Pavel Denisov, Xuankai Chang, Yushi Ueda, Yifan Peng, Yuekai Zhang, Sujay Kumar, Karthik Ganesan, Brian Yan, Ngoc Thang Vu, Alan W. Black, Shinji Watanabe:
ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet. CoRR abs/2111.14706 (2021) - [i39]Chia-Yu Li, Ngoc Thang Vu:
Improving Speech Recognition on Noisy Speech via Speech Enhancement with Multi-Discriminators CycleGAN. CoRR abs/2112.06309 (2021) - [i38]Chia-Yu Li, Ngoc Thang Vu:
Improving Code-switching Language Modeling with Artificially Generated Texts using Cycle-consistent Adversarial Networks. CoRR abs/2112.06327 (2021) - [i37]Injy Hamed, Alia El Bolock, Nader Rizk, Cornelia Herbert, Slim Abdennadher, Ngoc Thang Vu:
Predicting User Code-Switching Level from Sociological and Psychological Profiles. CoRR abs/2112.06462 (2021) - [i36]Chia-Yu Li, Ngoc Thang Vu:
Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognition. CoRR abs/2112.10108 (2021) - [i35]Chia-Yu Li, Ngoc Thang Vu:
Integrating Knowledge in End-to-End Automatic Speech Recognition for Mandarin-English Code-Switching. CoRR abs/2112.10202 (2021) - 2020
- [j3]Daniel Grießhaber, Ngoc Thang Vu, Johannes Maucher:
Low-resource text classification using domain-adversarial learning. Comput. Speech Lang. 62: 101056 (2020) - [j2]Sabrina Stehwien, Antje Schweitzer, Ngoc Thang Vu:
Acoustic and temporal representations in convolutional neural network models of prosodic events. Speech Commun. 125: 128-141 (2020) - [c89]