Hermann Ney

The RWTH/UPB system combination for the CHiME 2018 Workshop

2018

This paper describes the systems for the single-array track and the multiple-array track of the 5th CHiME Challenge. The final system is a combination of multiple systems, using Confusion Network Combination (CNC). The different systems …

Investigations on Phoneme-Based End-To-End Speech Recognition.

2020 · arXiv (Cornell University)

Common end-to-end models like CTC or encoder-decoder-attention models use characters or subword units like BPE as the output labels. We do systematic comparisons between grapheme-based and phoneme-based output labels. These can be single phonemes without …

Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer

2021

Evgeniia Tokarchuk, Jan Rosendahl, Weiyue Wang, Pavel Petrushkov, Tomer Lancewicki, Shahram Khadivi, Hermann Ney. Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021). 2021.

On Language Model Integration for RNN Transducer based Speech Recognition

2021 · arXiv (Cornell University)

The mismatch between an external language model (LM) and the implicitly learned internal LM (ILM) of RNN-Transducer (RNN-T) can limit the performance of LM integration such as simple shallow fusion. A Bayesian interpretation suggests to …

Efficient Utilization of Large Pre-Trained Models for Low Resource ASR

2023

Unsupervised representation learning has recently helped automatic speech recognition (ASR) to tackle tasks with limited labeled data. Following this, hardware limitations and applications give rise to the question how to take advantage of large pre-trained …

From Feedforward to Recurrent LSTM Neural Networks for Language Modeling

2015 · IEEE/ACM Transactions on Audio Speech and Language Processing

Language models have traditionally been estimated based on relative frequencies, using count statistics that can be extracted from huge amounts of text data. More recently, it has been found that neural networks are particularly powerful …

CharacTer: Translation Edit Rate on Character Level

2016

Recently, the capability of character-level evaluation measures for machine translation output has been confirmed by several metrics. This work proposes translation edit rate on character level (CharacTER), which calculates the character level edit distance while …

Improved Training of End-to-end Attention Models for Speech Recognition

2018

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h tasks. In particular, we …

Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies

2019

Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques to transfer a pre-trained NMT …

Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages

2019

Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.