| 2026 | LREC | Probing Discrete Speech Tokens of Spoken Language Models. | Sven Naber, Julia Koch, Pranav Singh, Alberto Saponaro, Ioanna Karagianni, Ngoc Thang Vu |
| 2025 | COLING | A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions. | Injy Hamed, Caroline Sabty, Slim Abdennadher, Ngoc Thang Vu, Thamar Solorio, Nizar Habash |
| 2025 | COLING | Discrete Subgraph Sampling for Interpretable Graph based Visual Question Answering. | Pascal Tilli, Ngoc Thang Vu |
| 2025 | COLING | It's What You Say and How You Say It: Investigating the Effect of Linguistic vs. Behavioral Adaptation in Task-Oriented Chatbots. | Lindsey Vanderlyn, Ngoc Thang Vu |
| 2025 | ICASSP | High-Resolution Speech Restoration with Latent Diffusion Model. | Tushar Dhyani, Florian Lux, Michele Mancusi, Giorgio Fabbro, Fritz Hohl, Ngoc Thang Vu |
| 2025 | ICASSP | What Affects the Performance of Fake Audio Detection? Analyzing Factors in a Continual Learning Setting. | Yixuan Xiao, Ngoc Thang Vu |
| 2025 | Interspeech | Investigating Stochastic Methods for Prosody Modeling in Speech Synthesis. | Paul Mayer, Florian Lux, Alejandro Prez Gonzlez de Martos, Angelina Elizarova, Lindsey Vanderlyn, Dirk Vth, Ngoc Thang Vu |
| 2025 | Interspeech | First Steps Towards Voice Anonymization for Code-Switching Speech. | Sarina Meyer, Ekaterina Kolos, Ngoc Thang Vu |
| 2025 | Interspeech | Layer-Wise Decision Fusion for Fake Audio Detection Using XLS-R. | Yixuan Xiao, Ngoc Thang Vu |
| 2025 | NAACL | Understanding the Role of Mental Models in User Interaction with an Adaptive Dialog Agent. | Lindsey Vanderlyn, Dirk Vth, Ngoc Thang Vu |
| 2024 | COLING | Prompting-based Synthetic Data Generation for Few-Shot Question Answering. | Maximilian Schmidt, Andrea Bartezzaghi, Ngoc Thang Vu |
| 2024 | COLING | Intrinsic Subgraph Generation for Interpretable Graph Based Visual Question Answering. | Pascal Tilli, Ngoc Thang Vu |
| 2024 | COLING | Towards a Zero-Data, Controllable, Adaptive Dialog System. | Dirk Vth, Lindsey Vanderlyn, Ngoc Thang Vu |
| 2024 | COLING | Explaining Pre-Trained Language Models with Attribution Scores: An Analysis in Low-Resource Settings. | Wei Zhou, Heike Adel, Hendrik Schuff, Ngoc Thang Vu |
| 2024 | ICANN | Combining Data Generation and Active Learning for Low-Resource Question Answering. | Maximilian Kimmich, Andrea Bartezzaghi, Jasmina Bogojeska, Cristiano Malossi, Ngoc Thang Vu |
| 2024 | Interspeech | Controlling Emotion in Text-to-Speech with Natural Language Prompts. | Thomas Bott, Florian Lux, Ngoc Thang Vu |
| 2024 | Interspeech | Meta Learning Text-to-Speech Synthesis in over 7000 Languages. | Florian Lux, Sarina Meyer, Lyonel Behringer, Frank Zalkow, Phat Do, Matt Coler, Emanul A. P. Habets, Ngoc Thang Vu |
| 2024 | Interspeech | Probing the Feasibility of Multilingual Speaker Anonymization. | Sarina Meyer, Florian Lux, Ngoc Thang Vu |
| 2023 | ACL | Neighboring Words Affect Human Interpretation of Saliency Explanations. | Alon Jacovi, Hendrik Schuff, Heike Adel, Ngoc Thang Vu, Yoav Goldberg |
| 2023 | ACL | Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers. | Manuel Mager, Elisabeth Mager, Katharina Kann, Ngoc Thang Vu |
| 2023 | ACL | DIAGRAPH: An Open-Source Graphic Interface for Dialog Flow Design. | Dirk Vth, Lindsey Vanderlyn, Ngoc Thang Vu |
| 2023 | ASRU | Leveraging Multilingual Self-Supervised Pretrained Models for Sequence-to-Sequence End-to-End Spoken Language Understanding. | Pavel Denisov, Ngoc Thang Vu |
| 2023 | CoNLL | HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities. | Esra Dnmez, Pascal Tilli, Hsiu-Yu Yang, Ngoc Thang Vu, Carina Silberer |
| 2023 | EACL | Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text. | Marwa Gaser, Manuel Mager, Injy Hamed, Nizar Habash, Slim Abdennadher, Ngoc Thang Vu |
| 2023 | EACL | Conversational Tree Search: A New Hybrid Dialog Task. | Dirk Vth, Lindsey Vanderlyn, Ngoc Thang Vu |
| 2023 | ICASSP | Prosody Is Not Identity: A Speaker Anonymization Approach Using Prosody Cloning. | Sarina Meyer, Florian Lux, Julia Koch, Pavel Denisov, Pascal Tilli, Ngoc Thang Vu |
| 2023 | IJCAI | Regularisation for Efficient Softmax Parameter Generation in Low-Resource Text Classifiers. | Daniel Griehaber, Johannes Maucher, Ngoc Thang Vu |
| 2023 | Interspeech | Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directions. | Florian Lux, Pascal Tilli, Sarina Meyer, Ngoc Thang Vu |
| 2023 | VINCI | Visual Analysis of Scene-Graph-Based Visual Question Answering. | Noel Schfer, Sebastian Knzel, Tanja Munz-Krner, Pascal Tilli, Sandeep Vidyapu, Ngoc Thang Vu, Daniel Weiskopf |
| 2022 | ACL | AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages. | Abteen Ebrahimi, Manuel Mager, Arturo Oncevay, Vishrav Chaudhary, Luis Chiruzzo, Angela Fan, John E. Ortega, Ricardo Ramos, Annette Rios, Ivn Vladimir Meza Ruz, Gustavo Gimnez Lugo, Elisabeth Mager, Graham Neubig, Alexis Palmer, Rolando Coto-Solano, Ngoc Thang Vu, Katharina Kann |
| 2022 | ACL | Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features. | Florian Lux, Ngoc Thang Vu |
| 2022 | ACL | BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages. | Manuel Mager, Arturo Oncevay, Elisabeth Mager, Katharina Kann, Ngoc Thang Vu |
| 2022 | ICASSP | ESPnet-SLU: Advancing Spoken Language Understanding Through ESPnet. | 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 |
| 2022 | IJCNLP | Low-Resource Multilingual and Zero-Shot Multispeaker TTS. | Florian Lux, Julia Koch, Ngoc Thang Vu |
| 2022 | IJCNLP | Toward Implicit Reference in Dialog: A Survey of Methods and Data. | Lindsey Vanderlyn, Talita Anthonio, Daniel Ortega, Michael Roth, Ngoc Thang Vu |
| 2022 | Interspeech | PoeticTTS - Controllable Poetry Reading for Literary Studies. | Julia Koch, Florian Lux, Nadja Schauffler, Toni Bernhart, Felix Dieterle, Jonas Kuhn, Sandra Richter, Gabriel Viehhauser, Ngoc Thang Vu |
| 2022 | Interspeech | Speaker Anonymization with Phonetic Intermediate Representations. | Sarina Meyer, Florian Lux, Pavel Denisov, Julia Koch, Pascal Tilli, Ngoc Thang Vu |
| 2022 | LREC | »textklang« - Towards a Multi-Modal Exploration Platform for German Poetry. | Nadja Schauffler, Toni Bernhart, Andr Blessing, Gunilla Eschenbach, Markus Grtner, Kerstin Jung, Anna Kinder, Julia Koch, Sandra Richter, Gabriel Viehhauser, Ngoc Thang Vu, Lorenz Wesemann, Jonas Kuhn |
| 2021 | ASRU | Improving Speech Recognition on Noisy Speech via Speech Enhancement with Multi-Discriminators CycleGAN. | Chia-Yu Li, Ngoc Thang Vu |
| 2021 | CoNLL | "It seemed like an annoying woman": On the Perception and Ethical Considerations of Affective Language in Text-Based Conversational Agents. | Lindsey Vanderlyn, Gianna Weber, Michael Neumann, Dirk Vth, Sarina Meyer, Ngoc Thang Vu |
| 2021 | CoNLL | "It's our fault!": Insights Into Users' Understanding and Interaction With an Explanatory Collaborative Dialog System. | Katharina Weitz, Lindsey Vanderlyn, Ngoc Thang Vu, Elisabeth Andr |
| 2021 | EACL | Few-shot Learning for Slot Tagging with Attentive Relational Network. | Cennet Oguz, Ngoc Thang Vu |
| 2021 | EMNLP | Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking. | Dirk Vth, Pascal Tilli, Ngoc Thang Vu |
| 2021 | ICASSP | Meta-Learning for Improving Rare Word Recognition in End-to-End ASR. | Florian Lux, Ngoc Thang Vu |
| 2020 | ACL | ADVISER: A Toolkit for Developing Multi-modal, Multi-domain and Socially-engaged Conversational Agents. | Chia-Yu Li, Daniel Ortega, Dirk Vth, Florian Lux, Lindsey Vanderlyn, Maximilian Schmidt, Michael Neumann, Moritz Vlkel, Pavel Denisov, Sabrina Jenne, Zorica Kacarevic, Ngoc Thang Vu |
| 2020 | ACL | Fast and Accurate Non-Projective Dependency Tree Linearization. | Xiang Yu, Simon Tannert, Ngoc Thang Vu, Jonas Kuhn |
| 2020 | AVI | ClaVis: An Interactive Visual Comparison System for Classifiers. | Frank Heyen, Tanja Munz, Michael Neumann, Daniel Ortega, Ngoc Thang Vu, Daniel Weiskopf, Michael Sedlmair |
| 2020 | COLING | Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning. | Daniel Griehaber, Johannes Maucher, Ngoc Thang Vu |
| 2020 | CoNLL | Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension. | Ekta Sood, Simon Tannert, Diego Frassinelli, Andreas Bulling, Ngoc Thang Vu |
| 2020 | EMNLP | A Two-stage Model for Slot Filling in Low-resource Settings: Domain-agnostic Non-slot Reduction and Pretrained Contextual Embeddings. | Cennet Oguz, Ngoc Thang Vu |
| 2020 | EMNLP | F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering. | Hendrik Schuff, Heike Adel, Ngoc Thang Vu |
| 2020 | ICASSP | OH, JEEZ! or UH-HUH? A Listener-Aware Backchannel Predictor on ASR Transcriptions. | Daniel Ortega, Chia-Yu Li, Ngoc Thang Vu |
| 2020 | Interspeech | Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning. | Pavel Denisov, Ngoc Thang Vu |
| 2020 | Interspeech | Improving Code-Switching Language Modeling with Artificially Generated Texts Using Cycle-Consistent Adversarial Networks. | Chia-Yu Li, Ngoc Thang Vu |
| 2020 | LREC | Cairo Student Code-Switch (CSCS) Corpus: An Annotated Egyptian Arabic-English Corpus. | Mohamed Balabel, Injy Hamed, Slim Abdennadher, Ngoc Thang Vu, zlem etinoglu |
| 2020 | LREC | ArzEn: A Speech Corpus for Code-switched Egyptian Arabic-English. | Injy Hamed, Ngoc Thang Vu, Slim Abdennadher |
| 2020 | PAAMS | Who, When and Why: The 3 Ws of Code-Switching. | Alia El Bolock, Injy Khairy, Yomna Abdelrahman, Ngoc Thang Vu, Cornelia Herbert, Slim Abdennadher |
| 2019 | ACL | ADVISER: A Dialog System Framework for Education & Research. | Daniel Ortega, Dirk Vth, Gianna Weber, Lindsey Vanderlyn, Maximilian Schmidt, Moritz Vlkel, Zorica Karacevic, Ngoc Thang Vu |
| 2019 | EMNLP | IMSurReal: IMS at the Surface Realization Shared Task 2019. | Xiang Yu, Agnieszka Falenska, Marina Haid, Ngoc Thang Vu, Jonas Kuhn |
| 2019 | ICASSP | Improving Speech Emotion Recognition with Unsupervised Representation Learning on Unlabeled Speech. | Michael Neumann, Ngoc Thang Vu |
| 2019 | ICASSP | Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions. | Daniel Ortega, Chia-Yu Li, Gisela Vallejo, Pavel Denisov, Ngoc Thang Vu |
| 2019 | INLG | Head-First Linearization with Tree-Structured Representation. | Xiang Yu, Agnieszka Falenska, Ngoc Thang Vu, Jonas Kuhn |
| 2019 | Interspeech | Automatic Compression of Subtitles with Neural Networks and its Effect on User Experience. | Katrin Angerbauer, Heike Adel, Ngoc Thang Vu |
| 2019 | Interspeech | CycleGAN-Based Emotion Style Transfer as Data Augmentation for Speech Emotion Recognition. | Fang Bao, Michael Neumann, Ngoc Thang Vu |
| 2019 | Interspeech | End-to-End Multi-Speaker Speech Recognition Using Speaker Embeddings and Transfer Learning. | Pavel Denisov, Ngoc Thang Vu |
| 2019 | Interspeech | Multimodal Articulation-Based Pronunciation Error Detection with Spectrogram and Acoustic Features. | Sabrina Jenne, Ngoc Thang Vu |
| 2019 | SIGdial | To Combine or Not To Combine? A Rainbow Deep Reinforcement Learning Agent for Dialog Policies. | Dirk Vth, Ngoc Thang Vu |
| 2018 | CoNLL | Comparing Attention-Based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension. | Matthias Blohm, Glorianna Jagfeld, Ekta Sood, Xiang Yu, Ngoc Thang Vu |
| 2018 | ICASSP | CRoss-lingual and Multilingual Speech Emotion Recognition on English and French. | Michael Neumann, Ngoc Thang Vu |
| 2018 | ICASSP | Lexico-Acoustic Neural-Based Models for Dialog Act Classification. | Daniel Ortega, Ngoc Thang Vu |
| 2018 | ICASSP | Investigations on End- to-End Audiovisual Fusion. | Michael Wand, Jrgen Schmidhuber, Ngoc Thang Vu |
| 2018 | INLG | Sequence-to-Sequence Models for Data-to-Text Natural Language Generation: Word- vs. Character-based Processing and Output Diversity. | Glorianna Jagfeld, Sabrina Jenne, Ngoc Thang Vu |
| 2018 | NAACL | Introducing Two Vietnamese Datasets for Evaluating Semantic Models of (Dis-)Similarity and Relatedness. | Kim Anh Nguyen, Sabine Schulte im Walde, Ngoc Thang Vu |
| 2017 | ACL | Character Composition Model with Convolutional Neural Networks for Dependency Parsing on Morphologically Rich Languages. | Xiang Yu, Ngoc Thang Vu |
| 2017 | EACL | Distinguishing Antonyms and Synonyms in a Pattern-based Neural Network. | Kim Anh Nguyen, Sabine Schulte im Walde, Ngoc Thang Vu |
| 2017 | EMNLP | Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking. | Glorianna Jagfeld, Ngoc Thang Vu |
| 2017 | EMNLP | Hierarchical Embeddings for Hypernymy Detection and Directionality. | Kim Anh Nguyen, Maximilian Kper, Sabine Schulte im Walde, Ngoc Thang Vu |
| 2017 | EMNLP | Improving coreference resolution with automatically predicted prosodic information. | Ina Rsiger, Sabrina Stehwien, Arndt Riester, Ngoc Thang Vu |
| 2017 | EMNLP | Enriching ASR Lattices with POS Tags for Dependency Parsing. | Moritz Stiefel, Ngoc Thang Vu |
| 2017 | EMNLP | A General-Purpose Tagger with Convolutional Neural Networks. | Xiang Yu, Agnieszka Falenska, Ngoc Thang Vu |
| 2017 | Interspeech | Attentive Convolutional Neural Network Based Speech Emotion Recognition: A Study on the Impact of Input Features, Signal Length, and Acted Speech. | Michael Neumann, Ngoc Thang Vu |
| 2017 | Interspeech | Prosodic Event Recognition Using Convolutional Neural Networks with Context Information. | Sabrina Stehwien, Ngoc Thang Vu |
| 2017 | SIGdial | Neural-based Context Representation Learning for Dialog Act Classification. | Daniel Ortega, Ngoc Thang Vu |
| 2016 | ACL | Integrating Distributional Lexical Contrast into Word Embeddings for Antonym-Synonym Distinction. | Kim Anh Nguyen, Sabine Schulte im Walde, Ngoc Thang Vu |
| 2016 | COLING | Neural-based Noise Filtering from Word Embeddings. | Kim Anh Nguyen, Sabine Schulte im Walde, Ngoc Thang Vu |
| 2016 | ICASSP | Bi-directional recurrent neural network with ranking loss for spoken language understanding. | Ngoc Thang Vu, Pankaj Gupta, Heike Adel, Hinrich Schtze |
| 2016 | Interspeech | Cross-Gender and Cross-Dialect Tone Recognition for Vietnamese. | Antje Schweitzer, Ngoc Thang Vu |
| 2016 | Interspeech | Exploring the Correlation of Pitch Accents and Semantic Slots for Spoken Language Understanding. | Sabrina Stehwien, Ngoc Thang Vu |
| 2016 | Interspeech | Sequential Convolutional Neural Networks for Slot Filling in Spoken Language Understanding. | Ngoc Thang Vu |
| 2016 | NAACL | Combining Recurrent and Convolutional Neural Networks for Relation Classification. | Ngoc Thang Vu, Heike Adel, Pankaj Gupta, Hinrich Schtze |
| 2014 | ICASSP | Multilingual deep neural network based acoustic modeling for rapid language adaptation. | Ngoc Thang Vu, David Imseng, Daniel Povey, Petr Motlcek, Tanja Schultz, Herv Bourlard |
| 2014 | Interspeech | Comparing approaches to convert recurrent neural networks into backoff language models for efficient decoding. | Heike Adel, Katrin Kirchhoff, Ngoc Thang Vu, Dominic Telaar, Tanja Schultz |
| 2014 | Interspeech | Combining recurrent neural networks and factored language models during decoding of code-Switching speech. | Heike Adel, Dominic Telaar, Ngoc Thang Vu, Katrin Kirchhoff, Tanja Schultz |
| 2014 | Interspeech | BioKIT - real-time decoder for biosignal processing. | Dominic Telaar, Michael Wand, Dirk Gehrig, Felix Putze, Christoph Amma, Dominic Heger, Ngoc Thang Vu, Mark Erhardt, Tim Schlippe, Matthias Janke, Christian Herff, Tanja Schultz |
| 2014 | Interspeech | Improving ASR performance on non-native speech using multilingual and crosslingual information. | Ngoc Thang Vu, Yuanfan Wang, Marten Klose, Zlatka Mihaylova, Tanja Schultz |
| 2014 | Interspeech | Investigating the learning effect of multilingual bottle-neck features for ASR. | Ngoc Thang Vu, Jochen Weiner, Tanja Schultz |
| 2013 | ACL | Combination of Recurrent Neural Networks and Factored Language Models for Code-Switching Language Modeling. | Heike Adel, Ngoc Thang Vu, Tanja Schultz |
| 2013 | ICASSP | Recurrent neural network language modeling for code switching conversational speech. | Heike Adel, Ngoc Thang Vu, Franziska Kraus, Tim Schlippe, Haizhou Li, Tanja Schultz |
| 2013 | ICASSP | GlobalPhone: A multilingual text & speech database in 20 languages. | Tanja Schultz, Ngoc Thang Vu, Tim Schlippe |
| 2013 | Interspeech | Experiments towards a better LVCSR system for tamil. | Melvin Jose Johnson Premkumar, Ngoc Thang Vu, Tanja Schultz |
| 2013 | Interspeech | Unsupervised language model adaptation for automatic speech recognition of broadcast news using web 2.0. | Tim Schlippe, Lukasz Gren, Ngoc Thang Vu, Tanja Schultz |
| 2013 | Interspeech | Multilingual multilayer perceptron for rapid language adaptation between and across language families. | Ngoc Thang Vu, Tanja Schultz |
| 2012 | ICASSP | Generating exact lattices in the WFST framework. | Daniel Povey, Mirko Hannemann, Gilles Boulianne, Luks Burget, Arnab Ghoshal, Milos Janda, Martin Karafit, Stefan Kombrink, Petr Motlcek, Yanmin Qian, Korbinian Riedhammer, Karel Vesel, Ngoc Thang Vu |
| 2012 | ICASSP | A first speech recognition system for Mandarin-English code-switch conversational speech. | Ngoc Thang Vu, Dau-Cheng Lyu, Jochen Weiner, Dominic Telaar, Tim Schlippe, Fabian Blaicher, Engsiong Chng, Tanja Schultz, Haizhou Li |
| 2012 | ICASSP | Modeling gender dependency in the Subspace GMM framework. | Ngoc Thang Vu, Tanja Schultz, Daniel Povey |
| 2012 | Interspeech | Automatic Error Recovery for Pronunciation Dictionaries. | Tim Schlippe, Sebastian Ochs, Ngoc Thang Vu, Tanja Schultz |
| 2012 | Interspeech | Initialization Schemes for Multilayer Perceptron Training and their Impact on ASR Performance using Multilingual Data. | Ngoc Thang Vu, Wojtek Breiter, Florian Metze, Tanja Schultz |
| 2011 | ICASSP | Cross-language bootstrapping based on completely unsupervised training using multilingual A-stabil. | Ngoc Thang Vu, Franziska Kraus, Tanja Schultz |
| 2011 | Interspeech | Rapid Building of an ASR System for Under-Resourced Languages Based on Multilingual Unsupervised Training. | Ngoc Thang Vu, Franziska Kraus, Tanja Schultz |
| 2010 | Interspeech | Rapid bootstrapping of five eastern european languages using the rapid language adaptation toolkit. | Ngoc Thang Vu, Tim Schlippe, Franziska Kraus, Tanja Schultz |
| 2009 | ASRU | Vietnamese large vocabulary continuous speech recognition. | Ngoc Thang Vu, Tanja Schultz |