Search Results for author: Alex Waibel

Found 95 papers, 5 papers with code

The 2017 KIT IWSLT Speech-to-Text Systems for English and German

no code implementations IWSLT 2017 Thai-Son Nguyen, Markus Müller, Matthias Sperber, Thomas Zenkel, Sebastian Stüker, Alex Waibel

For the English lecture task, our best combination system has a WER of 8. 3% on the tst2015 development set while our other combinations gained 25. 7% WER for German lecture tasks.

Toward Robust Neural Machine Translation for Noisy Input Sequences

no code implementations IWSLT 2017 Matthias Sperber, Jan Niehues, Alex Waibel

We note that unlike our baseline model, models trained on noisy data are able to generate outputs of proper length even for noisy inputs, while gradually reducing output length for higher amount of noise, as might also be expected from a human translator.

Machine Translation Translation

Domain-independent Punctuation and Segmentation Insertion

no code implementations IWSLT 2017 Eunah Cho, Jan Niehues, Alex Waibel

Experiments show that generalizing rare and unknown words greatly improves the punctuation insertion performance, reaching up to 8. 8 points of improvement in F-score when applied to the out-of-domain test scenario.

Machine Translation POS +2

The 2016 KIT IWSLT Speech-to-Text Systems for English and German

no code implementations IWSLT 2016 Thai-Son Nguyen, Markus Müller, Matthias Sperber, Thomas Zenkel, Kevin Kilgour, Sebastian Stüker, Alex Waibel

For the English TED task, our best combination system has a WER of 7. 8% on the development set while our other combinations gained 21. 8% and 28. 7% WERs for the English and German MSLT tasks.

Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience

no code implementations26 Sep 2024 Leonard Bärmann, Chad DeChant, Joana Plewnia, Fabian Peller-Konrad, Daniel Bauer, Tamim Asfour, Alex Waibel

Verbalization of robot experience, i. e., summarization of and question answering about a robot's past, is a crucial ability for improving human-robot interaction.

Language Modelling Large Language Model +1

Incremental Learning of Humanoid Robot Behavior from Natural Interaction and Large Language Models

no code implementations8 Sep 2023 Leonard Bärmann, Rainer Kartmann, Fabian Peller-Konrad, Jan Niehues, Alex Waibel, Tamim Asfour

In this paper, we propose a system to achieve incremental learning of complex behavior from natural interaction, and demonstrate its implementation on a humanoid robot.

Incremental Learning

Train Global, Tailor Local: Minimalist Multilingual Translation into Endangered Languages

no code implementations5 May 2023 Zhong Zhou, Jan Niehues, Alex Waibel

We examine two approaches: 1. best selection of seed sentences to jump start translations in a new language in view of best generalization to the remainder of a larger targeted text(s), and 2. we adapt large general multilingual translation engines from many other languages to focus on a specific text in a new, unknown language.

Humanitarian Translation

Adaptive multilingual speech recognition with pretrained models

no code implementations24 May 2022 Ngoc-Quan Pham, Alex Waibel, Jan Niehues

Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research.

speech-recognition Speech Recognition

Active Learning for Massively Parallel Translation of Constrained Text into Low Resource Languages

no code implementations MTSummit 2021 Zhong Zhou, Alex Waibel

We compare the portion-based approach that optimizes coherence of the text locally with the random sampling approach that increases coverage of the text globally.

Active Learning Machine Translation +1

Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation

no code implementations12 Apr 2021 Zhong Zhou, Alex Waibel

In other words, given a text in 124 source languages, we translate it into a severely low resource language using only ~1, 000 lines of low resource data without any external help.

Machine Translation Translation

Super-Human Performance in Online Low-latency Recognition of Conversational Speech

1 code implementation7 Oct 2020 Thai-Son Nguyen, Sebastian Stueker, Alex Waibel

Achieving super-human performance in recognizing human speech has been a goal for several decades, as researchers have worked on increasingly challenging tasks.

Decoder

FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN

no code implementations WS 2020 Ebrahim Ansari, Amittai Axelrod, Nguyen Bach, Ond{\v{r}}ej Bojar, Roldano Cattoni, Fahim Dalvi, Nadir Durrani, Marcello Federico, Christian Federmann, Jiatao Gu, Fei Huang, Kevin Knight, Xutai Ma, Ajay Nagesh, Matteo Negri, Jan Niehues, Juan Pino, Elizabeth Salesky, Xing Shi, Sebastian St{\"u}ker, Marco Turchi, Alex Waibel, er, Changhan Wang

The evaluation campaign of the International Conference on Spoken Language Translation (IWSLT 2020) featured this year six challenge tracks: (i) Simultaneous speech translation, (ii) Video speech translation, (iii) Offline speech translation, (iv) Conversational speech translation, (v) Open domain translation, and (vi) Non-native speech translation.

Translation

Towards Stream Translation: Adaptive Computation Time for Simultaneous Machine Translation

no code implementations WS 2020 Felix Schneider, Alex Waibel, er

Simultaneous machine translation systems rely on a policy to schedule read and write operations in order to begin translating a source sentence before it is complete.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

DaCToR: A Data Collection Tool for the RELATER Project

no code implementations LREC 2020 Juan Hussain, Oussama Zenkri, Sebastian St{\"u}ker, Alex Waibel

Collecting domain-specific data for under-resourced languages, e. g., dialects of languages, can be very expensive, potentially financially prohibitive and taking long time.

Error correction and extraction in request dialogs

no code implementations8 Apr 2020 Stefan Constantin, Alex Waibel

If yes, it corrects the second last utterance according to the error correction in the last utterance and outputs the extracted pairs of reparandum and repair entity.

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

no code implementations22 Mar 2020 Thai-Son Nguyen, Ngoc-Quan Pham, Sebastian Stueker, Alex Waibel

However, when it comes to performing run-on recognition on an input stream of audio data while producing recognition results in real-time and with low word-based latency, these models face several challenges.

speech-recognition Speech Recognition +1

Toward Cross-Domain Speech Recognition with End-to-End Models

no code implementations9 Mar 2020 Thai-Son Nguyen, Sebastian Stüker, Alex Waibel

We show that for the hybrid models, supplying additional training data from other domains with mismatched acoustic conditions does not increase the performance on specific domains.

speech-recognition Speech Recognition

Bimodal Speech Emotion Recognition Using Pre-Trained Language Models

no code implementations29 Nov 2019 Verena Heusser, Niklas Freymuth, Stefan Constantin, Alex Waibel

Speech emotion recognition is a challenging task and an important step towards more natural human-machine interaction.

Reinforcement Learning Speech Emotion Recognition

Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translation

no code implementations7 Nov 2019 Zhong Zhou, Lori Levin, David R. Mortensen, Alex Waibel

Firstly, we pool IGT for 1, 497 languages in ODIN (54, 545 glosses) and 70, 918 glosses in Arapaho and train a gloss-to-target NMT system from IGT to English, with a BLEU score of 25. 94.

Machine Translation NMT +2

Incremental processing of noisy user utterances in the spoken language understanding task

no code implementations WS 2019 Stefan Constantin, Jan Niehues, Alex Waibel

The state-of-the-art neural network architectures make it possible to create spoken language understanding systems with high quality and fast processing time.

Natural Language Understanding Spoken Language Understanding

Self-Attentional Models for Lattice Inputs

no code implementations ACL 2019 Matthias Sperber, Graham Neubig, Ngoc-Quan Pham, Alex Waibel

Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic analyses.

Computational Efficiency speech-recognition +2

Fluent Translations from Disfluent Speech in End-to-End Speech Translation

no code implementations NAACL 2019 Elizabeth Salesky, Matthias Sperber, Alex Waibel

Spoken language translation applications for speech suffer due to conversational speech phenomena, particularly the presence of disfluencies.

Machine Translation speech-recognition +2

Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation

no code implementations TACL 2019 Matthias Sperber, Graham Neubig, Jan Niehues, Alex Waibel

Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts.

Machine Translation speech-recognition +2

Learning Shared Encoding Representation for End-to-End Speech Recognition Models

no code implementations31 Mar 2019 Thai-Son Nguyen, Sebastian Stueker, Alex Waibel

In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria.

Deep Attention General Classification +2

Using multi-task learning to improve the performance of acoustic-to-word and conventional hybrid models

no code implementations2 Feb 2019 Thai-Son Nguyen, Sebastian Stueker, Alex Waibel

Acoustic-to-word (A2W) models that allow direct mapping from acoustic signals to word sequences are an appealing approach to end-to-end automatic speech recognition due to their simplicity.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Multi-task learning to improve natural language understanding

no code implementations17 Dec 2018 Stefan Constantin, Jan Niehues, Alex Waibel

When building a neural network-based Natural Language Understanding component, one main challenge is to collect enough training data.

Decoder Multi-Task Learning +1

Low-Latency Neural Speech Translation

no code implementations1 Aug 2018 Jan Niehues, Ngoc-Quan Pham, Thanh-Le Ha, Matthias Sperber, Alex Waibel

After adaptation, we are able to reduce the number of corrections displayed during incremental output construction by 45%, without a decrease in translation quality.

Machine Translation Multi-Task Learning +3

A Hierarchical Approach to Neural Context-Aware Modeling

no code implementations27 Jul 2018 Patrick Huber, Jan Niehues, Alex Waibel

Our approach overcomes recent limitations with extended narratives through a multi-layered computational approach to generate an abstract context representation.

Binary Classification Language Modelling +1

Robust and Scalable Differentiable Neural Computer for Question Answering

1 code implementation WS 2018 Jörg Franke, Jan Niehues, Alex Waibel

Deep learning models are often not easily adaptable to new tasks and require task-specific adjustments.

Question Answering

Neural Language Codes for Multilingual Acoustic Models

no code implementations5 Jul 2018 Markus Müller, Sebastian Stüker, Alex Waibel

Multilingual Speech Recognition is one of the most costly AI problems, because each language (7, 000+) and even different accents require their own acoustic models to obtain best recognition performance.

speech-recognition Speech Recognition

Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation

no code implementations WS 2018 Zhong Zhou, Matthias Sperber, Alex Waibel

The main challenges we identify are the lack of low-resource language data, effective methods for cross-lingual transfer, and the variable-binding problem that is common in neural systems.

Cross-Lingual Transfer Translation

Self-Attentional Acoustic Models

1 code implementation26 Mar 2018 Matthias Sperber, Jan Niehues, Graham Neubig, Sebastian Stüker, Alex Waibel

Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities.

Automated Evaluation of Out-of-Context Errors

1 code implementation LREC 2018 Patrick Huber, Jan Niehues, Alex Waibel

We present a new approach to evaluate computational models for the task of text understanding by the means of out-of-context error detection.

Binary Classification Language Modelling +2

An End-to-End Goal-Oriented Dialog System with a Generative Natural Language Response Generation

no code implementations6 Mar 2018 Stefan Constantin, Jan Niehues, Alex Waibel

Furthermore, by using a feedforward neural network, we are able to generate the output word by word and are no longer restricted to a fixed number of possible response candidates.

Goal-Oriented Dialog Response Generation

Subword and Crossword Units for CTC Acoustic Models

no code implementations19 Dec 2017 Thomas Zenkel, Ramon Sanabria, Florian Metze, Alex Waibel

This paper proposes a novel approach to create an unit set for CTC based speech recognition systems.

Language Modelling speech-recognition +1

Multilingual Adaptation of RNN Based ASR Systems

no code implementations13 Nov 2017 Markus Müller, Sebastian Stüker, Alex Waibel

In this work, we focus on multilingual systems based on recurrent neural networks (RNNs), trained using the Connectionist Temporal Classification (CTC) loss function.

Transcribing Against Time

no code implementations15 Sep 2017 Matthias Sperber, Graham Neubig, Jan Niehues, Satoshi Nakamura, Alex Waibel

We investigate the problem of manually correcting errors from an automatic speech transcript in a cost-sensitive fashion.

Analyzing Neural MT Search and Model Performance

no code implementations WS 2017 Jan Niehues, Eunah Cho, Thanh-Le Ha, Alex Waibel

By separating the search space and the modeling using $n$-best list reranking, we analyze the influence of both parts of an NMT system independently.

NMT Translation

Yeah, Right, Uh-Huh: A Deep Learning Backchannel Predictor

1 code implementation2 Jun 2017 Robin Ruede, Markus Müller, Sebastian Stüker, Alex Waibel

BCs can be expressed in different ways, depending on the modality of the interaction, for example as gestures or acoustic cues.

Deep Learning

Neural Lattice-to-Sequence Models for Uncertain Inputs

no code implementations EMNLP 2017 Matthias Sperber, Graham Neubig, Jan Niehues, Alex Waibel

In this work, we extend the TreeLSTM (Tai et al., 2015) into a LatticeLSTM that is able to consume word lattices, and can be used as encoder in an attentional encoder-decoder model.

Decoder Translation

Lightly Supervised Quality Estimation

no code implementations COLING 2016 Matthias Sperber, Graham Neubig, Jan Niehues, Sebastian St{\"u}ker, Alex Waibel

Evaluating the quality of output from language processing systems such as machine translation or speech recognition is an essential step in ensuring that they are sufficient for practical use.

Automatic Speech Recognition (ASR) Machine Translation +2

Evaluation of the KIT Lecture Translation System

no code implementations LREC 2016 Markus M{\"u}ller, Sarah F{\"u}nfer, Sebastian St{\"u}ker, Alex Waibel

One obstacle to achieving this goal is that lectures at KIT are usually held in German which many foreign students are not sufficiently proficient in, as, e. g., opposed to English.

Translation

Lexical Translation Model Using a Deep Neural Network Architecture

no code implementations28 Apr 2015 Thanh-Le Ha, Jan Niehues, Alex Waibel

In this paper we combine the advantages of a model using global source sentence contexts, the Discriminative Word Lexicon, and neural networks.

Sentence Translation

The KIT Lecture Corpus for Speech Translation

no code implementations LREC 2012 Sebastian St{\"u}ker, Florian Kraft, Christian Mohr, Teresa Herrmann, Eunah Cho, Alex Waibel

Academic lectures offer valuable content, but often do not reach their full potential audience due to the language barrier.

Speech Recognition Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.