M
Matthias Sperber
Researcher at Apple Inc.
Publications - 59
Citations - 1142
Matthias Sperber is an academic researcher from Apple Inc.. The author has contributed to research in topics: Speech translation & Machine translation. The author has an hindex of 16, co-authored 55 publications receiving 815 citations. Previous affiliations of Matthias Sperber include Karlsruhe Institute of Technology & Kaiserslautern University of Technology.
Papers
More filters
Journal ArticleDOI
Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation
TL;DR: This paper demonstrates that direct speech translation models require more data to perform well and is able to exploit auxiliary training data much more effectively than direct attentional models, and proposes an attention-passing technique that alleviates error propagation issues in a previous formulation of a model with two attention stages.
Proceedings ArticleDOI
Self-Attentional Acoustic Models
TL;DR: In this article, the authors apply self-attention to acoustic modeling, and propose a Gaussian biasing approach that allows explicit control over the context range, and demonstrate that interpretability is a strength of selfattentional acoustic models.
Proceedings ArticleDOI
Speech Translation and the End-to-End Promise: Taking Stock of Where We Are.
Matthias Sperber,Matthias Paulik +1 more
TL;DR: A unifying categorization and nomenclature that covers both traditional and recent approaches and that may help researchers by highlighting both trade-offs and open research questions is provided.
Proceedings ArticleDOI
Findings of the IWSLT 2022 Evaluation Campaign
Antonios Anastasopoulos,Loïc Barrault,Luisa Bentivogli,Marcely Zanon Boito,Ondřej Bojar,Roldano Cattoni,Anna Currey,Georgiana Dinu,Kevin K. Duh,Maha Elbayad,Clara Emmanuel,Yannick Estève,Margarita Frederico,Christian Federmann,Souhir Gahbiche,Hongyu Gong,Roman Grundkiewicz,Barry Haddow,Benjamin Hsu,Dávid Javorský,Věra Kloudová,Surafel Melaku Lakew,Xutai Ma,Prashant Mathur,Paul McNamee,Kenton Murray,Maria Nadejde,Satoshi Nakamura,M. Cristina Negri,Jan Niehues,Xing Niu,John Ortega,Juan Pino,Elizabeth Salesky,Jiatong Shi,Matthias Sperber,Sebastian Stüker,K. Sudoh,Marco Turchi,Yogesh Virkar,Alex Waibel,Chang Wang,Shinji Watanabe +42 more
TL;DR: For each shared task of the 19th International Conference on Spoken Language Translation, the purpose of the task, the data that were released, the evaluation metrics that were applied, the submissions that were received and the results that were achieved are detailed.
Proceedings ArticleDOI
Neural Lattice-to-Sequence Models for Uncertain Inputs
TL;DR: This work extends the TreeL STM into a LatticeLSTM that is able to consume word lattices, and can be used as encoder in an attentional encoder-decoder model, and integrates lattice posterior scores into this architecture.