C
Christian Fuegen
Researcher at Facebook
Publications - 53
Citations - 1366
Christian Fuegen is an academic researcher from Facebook. The author has contributed to research in topics: Word error rate & Language model. The author has an hindex of 12, co-authored 50 publications receiving 761 citations. Previous affiliations of Christian Fuegen include Karlsruhe Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Transformer-Based Acoustic Modeling for Hybrid Speech Recognition
Yongqiang Wang,Abdelrahman Mohamed,Due Le,Chunxi Liu,Alex Xiao,Jay Mahadeokar,Hongzhao Huang,Andros Tjandra,Xiaohui Zhang,Frank Zhang,Christian Fuegen,Geoffrey Zweig,Michael L. Seltzer +12 more
TL;DR: This article proposed and evaluated transformer-based acoustic models (AMs) for hybrid speech recognition, including various positional embedding methods and an iterated loss to enable training deep transformers.
Proceedings ArticleDOI
Libri-Light: A Benchmark for ASR with Limited or No Supervision
Jacob Kahn,Morgane Riviere,Weiyi Zheng,Eugene Kharitonov,Qiantong Xu,Pierre-Emmanuel Mazaré,Julien Karadayi,Vitaliy Liptchinsky,Ronan Collobert,Christian Fuegen,Tatiana Likhomanenko,Gabriel Synnaeve,Armand Joulin,Abdelrahman Mohamed,Emmanuel Dupoux +14 more
TL;DR: In this article, the authors introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision, which is derived from open-source audio books from the LibriVox project.
Proceedings ArticleDOI
Towards End-to-end Spoken Language Understanding
TL;DR: This study showed that the trained model can achieve reasonable good result and demonstrated that the model can capture the semantic attention directly from the audio features.
Posted Content
Transformer-Transducer: End-to-End Speech Recognition with Self-Attention
Ching-Feng Yeh,Jay Mahadeokar,Kaustubh Kalgaonkar,Yongqiang Wang,Duc Le,Mahaveer Jain,Kjell Schubert,Christian Fuegen,Michael L. Seltzer +8 more
TL;DR: The proposed Transformer-Transducer outperforms neural transducer with LSTM/BLSTM networks and achieved word error rates of 6.37 % on the test-clean set and 15.30%) while remaining streamable, compact, and computationally efficient with complexity of O(T), where T is input sequence length.
Patent
Hybrid, offline/online speech translation system
TL;DR: In this article, a hybrid speech translation system is proposed, where a wireless-enabled client computing device can translate input speech utterances from one language to another locally, and also, in an online mode when there is wireless network connectivity, have a remote computer perform the translation and transmit it back to the client computing devices via the wireless network for audible outputting by client devices.