b'Ngoc Thang Vu'

research

∙ 05/31/2023

Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers

In recent years machine translation has become very successful for high-...

0 Manuel Mager, et al. ∙

research

∙ 05/04/2023

Neighboring Words Affect Human Interpretation of Saliency Explanations

Word-level saliency explanations ("heat maps over words") are often used...

0 Alon Jacovi, et al. ∙

research

∙ 04/10/2023

Oh, Jeez! or Uh-huh? A Listener-aware Backchannel Predictor on ASR Transcriptions

This paper presents our latest investigation on modeling backchannel in ...

0 Daniel Ortega, et al. ∙

research

∙ 04/10/2023

Modeling Speaker-Listener Interaction for Backchannel Prediction

We present our latest findings on backchannel modeling novelly motivated...

0 Daniel Ortega, et al. ∙

research

∙ 03/17/2023

Conversational Tree Search: A New Hybrid Dialog Task

Conversational interfaces provide a flexible and easy way for users to s...

0 Dirk Väth, et al. ∙

research

∙ 11/22/2022

ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic - English

We present our work on collecting ArzEn-ST, a code-switched Egyptian Ara...

0 Injy Hamed, et al. ∙

research

∙ 10/21/2022

Low-Resource Multilingual and Zero-Shot Multispeaker TTS

While neural methods for text-to-speech (TTS) have shown great advances ...

0 Florian Lux, et al. ∙

research

∙ 10/20/2022

Improving Semi-supervised End-to-end Automatic Speech Recognition using CycleGAN and Inter-domain Losses

We propose a novel method that combines CycleGAN and inter-domain losses...

0 Chia Yu Li, et al. ∙

research

∙ 10/13/2022

How (Not) To Evaluate Explanation Quality

The importance of explainability is increasingly acknowledged in natural...

0 Hendrik Schuff, et al. ∙

research

∙ 10/13/2022

Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy

In order to protect the privacy of speech data, speaker anonymization ai...

0 Sarina Meyer, et al. ∙

research

∙ 10/11/2022

Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text

Data sparsity is one of the main challenges posed by Code-switching (CS)...

0 Marwa Gaser, et al. ∙

research

∙ 07/31/2022

The Who in Code-Switching: A Case Study for Predicting Egyptian Arabic-English Code-Switching Levels based on Character Profiles

Code-switching (CS) is a common linguistic phenomenon exhibited by multi...

0 Injy Hamed, et al. ∙

research

∙ 07/11/2022

PoeticTTS – Controllable Poetry Reading for Literary Studies

Speech synthesis for poetry is challenging due to specific intonation pa...

0 Julia Koch, et al. ∙

research

∙ 07/11/2022

Speaker Anonymization with Phonetic Intermediate Representations

In this work, we propose a speaker anonymization pipeline that leverages...

0 Sarina Meyer, et al. ∙

research

∙ 06/24/2022

Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech

The cloning of a speaker's voice using an untranscribed reference sample...

0 Florian Lux, et al. ∙

research

∙ 05/25/2022

Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation

Code-switching (CS) poses several challenges to NLP tasks, where data sp...

0 Injy Hamed, et al. ∙

research

∙ 05/03/2022

Meta Learning for Natural Language Processing: A Survey

Deep learning has been the mainstream technique in natural language proc...

0 Hung-Yi Lee, et al. ∙

research

∙ 03/16/2022

BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages

Morphologically-rich polysynthetic languages present a challenge for NLP...

0 Manuel Mager, et al. ∙

research

∙ 03/07/2022

Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features

While neural text-to-speech systems perform remarkably well in high-reso...

0 Florian Lux, et al. ∙

research

∙ 01/27/2022

Human Interpretation of Saliency-based Explanation Over Text

While a lot of research in explainable AI focuses on producing effective...

14 Hendrik Schuff, et al. ∙

research

∙ 12/19/2021

Integrating Knowledge in End-to-End Automatic Speech Recognition for Mandarin-English Code-Switching

Code-Switching (CS) is a common linguistic phenomenon in multilingual co...

0 Chia Yu Li, et al. ∙

research

∙ 12/19/2021

Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognition

We investigate densely connected convolutional networks (DenseNets) and ...

0 Chia Yu Li, et al. ∙

research

∙ 12/13/2021

Predicting User Code-Switching Level from Sociological and Psychological Profiles

Multilingual speakers tend to alternate between languages within a conve...

0 Injy Hamed, et al. ∙

research

∙ 12/12/2021

Improving Code-switching Language Modeling with Artificially Generated Texts using Cycle-consistent Adversarial Networks

This paper presents our latest effort on improving Code-switching langua...

0 Chia Yu Li, et al. ∙

research

∙ 12/12/2021

Improving Speech Recognition on Noisy Speech via Speech Enhancement with Multi-Discriminators CycleGAN

This paper presents our latest investigations on improving automatic spe...

0 Chia Yu Li, et al. ∙

research

∙ 11/29/2021

ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet

As Automatic Speech Processing (ASR) systems are getting better, there i...

0 Siddhant Arora, et al. ∙

research

∙ 10/11/2021

Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking

On the way towards general Visual Question Answering (VQA) systems that ...

0 Dirk Väth, et al. ∙

research

∙ 09/16/2021

Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings

Natural language inference (NLI) requires models to learn and apply comm...

0 Hendrik Schuff, et al. ∙

research

∙ 08/29/2021

Investigations on Speech Recognition Systems for Low-Resource Dialectal Arabic-English Code-Switching Speech

Code-switching (CS), defined as the mixing of languages in conversations...

0 Injy Hamed, et al. ∙

research

∙ 07/26/2021

Thought Flow Nets: From Single Predictions to Trains of Model Thought

When humans solve complex problems, they rarely come up with a decision ...

0 Hendrik Schuff, et al. ∙

research

∙ 06/30/2021

IMS' Systems for the IWSLT 2021 Low-Resource Speech Translation Task

This paper describes the submission to the IWSLT 2021 Low-Resource Speec...

0 Pavel Denisov, et al. ∙

research

∙ 04/18/2021

AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages

Pretrained multilingual models are able to perform cross-lingual transfe...

12 Abteen Ebrahimi, et al. ∙

research

∙ 03/03/2021

Few-shot Learning for Slot Tagging with Attentive Relational Network

Metric-based learning is a well-known family of methods for few-shot lea...

0 Cennet Oguz, et al. ∙

research

∙ 03/02/2021

Investigations on Audiovisual Emotion Recognition in Noisy Conditions

In this paper we explore audiovisual emotion recognition under noisy aco...

0 Michael Neumann, et al. ∙

research

∙ 02/25/2021

Meta-Learning for improving rare word recognition in end-to-end ASR

We propose a new method of generating meaningful embeddings for speech, ...

0 Florian Lux, et al. ∙

research

∙ 12/04/2020

Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning

Recently, leveraging pre-trained Transformer based language models in do...

0 Daniel Grießhaber, et al. ∙

research

∙ 10/13/2020

Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension

While neural networks with attention mechanisms have achieved superior p...

0 Ekta Sood, et al. ∙

research

∙ 10/13/2020

F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering

Explainable question answering systems predict an answer together with a...

0 Hendrik Schuff, et al. ∙

research

∙ 07/03/2020

Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning

Spoken language understanding is typically based on pipeline architectur...

0 Pavel Denisov, et al. ∙

research

∙ 05/04/2020

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

We present ADVISER - an open-source, multi-domain dialog system toolkit ...

2 Chia Yu Li, et al. ∙

research

∙ 09/24/2019

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

Code-switching (CS) is a widespread phenomenon among bilingual and multi...

0 Injy Hamed, et al. ∙

research

∙ 08/13/2019

IMS-Speech: A Speech to Text Tool

We present the IMS-Speech, a web based tool for German and English speec...

0 Pavel Denisov, et al. ∙

research

∙ 08/13/2019

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

This paper presents our latest investigation on end-to-end automatic spe...

0 Pavel Denisov, et al. ∙

research

∙ 02/28/2019

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

This paper presents our latest investigations on dialog act (DA) classif...

0 Daniel Ortega, et al. ∙

research

∙ 10/11/2018

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

We present a comparison of word-based and character-based sequence-to-se...

0 Glorianna Jagfeld, et al. ∙

research

∙ 08/27/2018

Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension

We propose a machine reading comprehension model based on the compare-ag...

0 Matthias Blohm, et al. ∙

research

∙ 08/10/2018

Densely Connected Convolutional Networks for Speech Recognition

This paper presents our latest investigation on Densely Connected Convol...

0 Chia Yu Li, et al. ∙

research

∙ 07/30/2018

Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition

In this paper, we investigate the use of adversarial learning for unsupe...

4 Pavel Denisov, et al. ∙

research

∙ 07/13/2018

Low-Resource Text Classification using Domain-Adversarial Learning

Deep learning techniques have recently shown to be successful in many na...

0 Daniel Grießhaber, et al. ∙

research

∙ 05/14/2018

Effects of Word Embeddings on Neural Network-based Pitch Accent Detection

Pitch accent detection often makes use of both acoustic and lexical feat...

0 Sabrina Stehwien, et al. ∙

Ngoc Thang Vu

Featured Co-authors