Search Results for author: Matthias Sperber

Found 34 papers, 4 papers with code

Findings of the IWSLT 2022 Evaluation Campaign

no code implementations IWSLT (ACL) 2022 Antonios Anastasopoulos, Loïc Barrault, Luisa Bentivogli, Marcely Zanon Boito, Ondřej Bojar, Roldano Cattoni, Anna Currey, Georgiana Dinu, Kevin Duh, Maha Elbayad, Clara Emmanuel, Yannick Estève, Marcello Federico, Christian Federmann, Souhir Gahbiche, Hongyu Gong, Roman Grundkiewicz, Barry Haddow, Benjamin Hsu, Dávid Javorský, Vĕra Kloudová, Surafel Lakew, Xutai Ma, Prashant Mathur, Paul McNamee, Kenton Murray, Maria Nǎdejde, Satoshi Nakamura, Matteo Negri, Jan Niehues, Xing Niu, John Ortega, Juan Pino, Elizabeth Salesky, Jiatong Shi, Matthias Sperber, Sebastian Stüker, Katsuhito Sudoh, Marco Turchi, Yogesh Virkar, Alexander Waibel, Changhan Wang, Shinji Watanabe

The evaluation campaign of the 19th International Conference on Spoken Language Translation featured eight shared tasks: (i) Simultaneous speech translation, (ii) Offline speech translation, (iii) Speech to speech translation, (iv) Low-resource speech translation, (v) Multilingual speech translation, (vi) Dialect speech translation, (vii) Formality control for speech translation, (viii) Isometric speech translation.

Speech-to-Speech Translation Translation

Audio Segmentation for Robust Real-Time Speech Recognition Based on Neural Networks

no code implementations IWSLT 2016 Micha Wetzel, Matthias Sperber, Alexander Waibel

Speech that contains multimedia content can pose a serious challenge for real-time automatic speech recognition (ASR) for two reasons: (1) The ASR produces meaningless output, hurting the readability of the transcript.

Automatic Speech Recognition Frame

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

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.

KIT’s Multilingual Neural Machine Translation systems for IWSLT 2017

no code implementations IWSLT 2017 Ngoc-Quan Pham, Matthias Sperber, Elizabeth Salesky, Thanh-Le Ha, Jan Niehues, Alexander Waibel

For the SLT track, in addition to a monolingual neural translation system used to generate correct punctuations and true cases of the data prior to training our multilingual system, we introduced a noise model in order to make our system more robust.

Machine Translation Translation

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.

Streaming Models for Joint Speech Recognition and Translation

no code implementations EACL 2021 Orion Weller, Matthias Sperber, Christian Gollan, Joris Kluivers

However, all previous work has only looked at this problem from the consecutive perspective, leaving uncertainty on whether these approaches are effective in the more challenging streaming setting.

Automatic Speech Recognition Translation

Consistent Transcription and Translation of Speech

1 code implementation24 Jul 2020 Matthias Sperber, Hendra Setiawan, Christian Gollan, Udhyakumar Nallasamy, Matthias Paulik

To address various shortcomings of this paradigm, recent work explores end-to-end trainable direct models that translate without transcribing.

Speech Recognition Translation

Variational Neural Machine Translation with Normalizing Flows

no code implementations ACL 2020 Hendra Setiawan, Matthias Sperber, Udhay Nallasamy, Matthias Paulik

Variational Neural Machine Translation (VNMT) is an attractive framework for modeling the generation of target translations, conditioned not only on the source sentence but also on some latent random variables.

Machine Translation Translation

Speech Translation and the End-to-End Promise: Taking Stock of Where We Are

no code implementations ACL 2020 Matthias Sperber, Matthias Paulik

Over its three decade history, speech translation has experienced several shifts in its primary research themes; moving from loosely coupled cascades of speech recognition and machine translation, to exploring questions of tight coupling, and finally to end-to-end models that have recently attracted much attention.

Machine Translation Speech Recognition +1

Low Latency ASR for Simultaneous Speech Translation

no code implementations22 Mar 2020 Thai Son Nguyen, Jan Niehues, Eunah Cho, Thanh-Le Ha, Kevin Kilgour, Markus Muller, Matthias Sperber, Sebastian Stueker, Alex Waibel

User studies have shown that reducing the latency of our simultaneous lecture translation system should be the most important goal.

Automatic Speech Recognition Translation

Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation

no code implementations ACL 2019 Elizabeth Salesky, Matthias Sperber, Alan W. black

Previous work on end-to-end translation from speech has primarily used frame-level features as speech representations, which creates longer, sparser sequences than text.

Frame Translation

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.

Speech Recognition Translation

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 +1

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 +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 +1

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.

XNMT: The eXtensible Neural Machine Translation Toolkit

1 code implementation WS 2018 Graham Neubig, Matthias Sperber, Xinyi Wang, Matthieu Felix, Austin Matthews, Sarguna Padmanabhan, Ye Qi, Devendra Singh Sachan, Philip Arthur, Pierre Godard, John Hewitt, Rachid Riad, Liming Wang

In this paper we describe the design of XNMT and its experiment configuration system, and demonstrate its utility on the tasks of machine translation, speech recognition, and multi-tasked machine translation/parsing.

Machine Translation Speech Recognition +1

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.

Comparison of Decoding Strategies for CTC Acoustic Models

no code implementations15 Aug 2017 Thomas Zenkel, Ramon Sanabria, Florian Metze, Jan Niehues, Matthias Sperber, Sebastian Stüker, Alex Waibel

The CTC loss function maps an input sequence of observable feature vectors to an output sequence of symbols.

Speech Recognition

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.

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 Machine Translation +1

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