265 citations · 1.1k across the 50 of their papers we have counts for
8 papers · 1 filter
Modeling Confidence in Sequence-to-Sequence Models
Jan Niehues, Ngoc-Quan Pham
Recently, significant improvements have been achieved in various natural language processing tasks using neural sequence-to-sequence models. While aiming for the best generation qu…
Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation
Thai-Son Nguyen, Sebastian Stueker, Jan Niehues +1
Sequence-to-Sequence (S2S) models recently started to show state-of-the-art performance for automatic speech recognition (ASR). With these large and deep models overfitting remains…
Incremental processing of noisy user utterances in the spoken language understanding task
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. One major challenge f…
Second-order QCD corrections to event shape distributions in deep inelastic scattering
T. Gehrmann, A. Huss, J. Mo +1
We compute the next-to-next-to-leading order (NNLO) QCD corrections to event shape distributions and their mean values in deep inelastic lepton-nucleon scattering. The magnitude an…
Improving Zero-shot Translation with Language-Independent Constraints
Ngoc-Quan Pham, Jan Niehues, Thanh-Le Ha +1
An important concern in training multilingual neural machine translation (NMT) is to translate between language pairs unseen during training, i.e zero-shot translation. Improving t…
Calculations for deep inelastic scattering using fast interpolation grid techniques at NNLO in QCD and the extraction of from HERA data
D. Britzger, J. Currie, A. Gehrmann-De Ridder +9
The extension of interpolation-grid frameworks for perturbative QCD calculations at next-to-next-to-leading order (NNLO) is presented for deep inelastic scattering (DIS) processes.…
Very Deep Self-Attention Networks for End-to-End Speech Recognition
Ngoc-Quan Pham, Thai-Son Nguyen, Jan Niehues +3
Recently, end-to-end sequence-to-sequence models for speech recognition have gained significant interest in the research community. While previous architecture choices revolve arou…
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…