55 citations · 99 across the 13 of their papers we have counts for
20 papers
Automating Behavioral Testing in Machine Translation
Javier Ferrando, Matthias Sperber, Hendra Setiawan +2
Behavioral testing in NLP allows fine-grained evaluation of systems by examining their linguistic capabilities through the analysis of input-output behavior. Unfortunately, existin…
Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data
Mozhdeh Gheini, Tatiana Likhomanenko, Matthias Sperber +1
Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, la…
End-to-End Speech Translation for Code Switched Speech
Orion Weller, Matthias Sperber, Telmo Pires +4
Code switching (CS) refers to the phenomenon of interchangeably using words and phrases from different languages. CS can pose significant accuracy challenges to NLP, due to the oft…
Streaming Models for Joint Speech Recognition and Translation
Orion Weller, Matthias Sperber, Christian Gollan +1
Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly convertin…
Consistent Transcription and Translation of Speech
Matthias Sperber, Hendra Setiawan, Christian Gollan +2
The conventional paradigm in speech translation starts with a speech recognition step to generate transcripts, followed by a translation step with the automatic transcripts as inpu…
Variational Neural Machine Translation with Normalizing Flows
Hendra Setiawan, Matthias Sperber, Udhay Nallasamy +1
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…
Speech Translation and the End-to-End Promise: Taking Stock of Where We Are
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 mach…
Low Latency ASR for Simultaneous Speech Translation
Thai Son Nguyen, Jan Niehues, Eunah Cho +6
User studies have shown that reducing the latency of our simultaneous lecture translation system should be the most important goal. We therefore have worked on several techniques f…
Self-Attentional Models for Lattice Inputs
Matthias Sperber, Graham Neubig, Ngoc-Quan Pham +1
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 recogn…
Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation
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. We show th…
Fluent Translations from Disfluent Speech in End-to-End Speech Translation
Elizabeth Salesky, Matthias Sperber, Alex Waibel
Spoken language translation applications for speech suffer due to conversational speech phenomena, particularly the presence of disfluencies. With the rise of end-to-end speech tra…
Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation
Matthias Sperber, Graham Neubig, Jan Niehues +1
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…
Paraphrases as Foreign Languages in Multilingual Neural Machine Translation
Zhong Zhou, Matthias Sperber, Alex Waibel
Paraphrases, the rewordings of the same semantic meaning, are useful for improving generalization and translation. However, prior works only explore paraphrases at the word or phra…
Low-Latency Neural Speech Translation
Jan Niehues, Ngoc-Quan Pham, Thanh-Le Ha +2
Through the development of neural machine translation, the quality of machine translation systems has been improved significantly. By exploiting advancements in deep learning, syst…
Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation
Zhong Zhou, Matthias Sperber, Alex Waibel
We work on translation from rich-resource languages to low-resource languages. The main challenges we identify are the lack of low-resource language data, effective methods for cro…
Self-Attentional Acoustic Models
Matthias Sperber, Jan Niehues, Graham Neubig +2
Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising resul…
XNMT: The eXtensible Neural Machine Translation Toolkit
Graham Neubig, Matthias Sperber, Xinyi Wang +10
This paper describes XNMT, the eXtensible Neural Machine Translation toolkit. XNMT distin- guishes itself from other open-source NMT toolkits by its focus on modular code design, w…
Transcribing Against Time
Matthias Sperber, Graham Neubig, Jan Niehues +2
We investigate the problem of manually correcting errors from an automatic speech transcript in a cost-sensitive fashion. This is done by specifying a fixed time budget, and then a…
Comparison of Decoding Strategies for CTC Acoustic Models
Thomas Zenkel, Ramon Sanabria, Florian Metze +4
Connectionist Temporal Classification has recently attracted a lot of interest as it offers an elegant approach to building acoustic models (AMs) for speech recognition. The CTC lo…
Neural Lattice-to-Sequence Models for Uncertain Inputs
Matthias Sperber, Graham Neubig, Jan Niehues +1
The input to a neural sequence-to-sequence model is often determined by an up-stream system, e.g. a word segmenter, part of speech tagger, or speech recognizer. These up-stream mod…