282 citations · 1.2k across the 80 of their papers we have counts for
88 papers
On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers
Zijian Yang, Wei Zhou, Ralf Schlüter +1
Internal language model (ILM) subtraction has been widely applied to improve the performance of the RNN-Transducer with external language model (LM) fusion for speech recognition.…
Chunked Attention-based Encoder-Decoder Model for Streaming Speech Recognition
Mohammad Zeineldeen, Albert Zeyer, Ralf Schlüter +1
We study a streamable attention-based encoder-decoder model in which either the decoder, or both the encoder and decoder, operate on pre-defined, fixed-size windows called chunks.…
Competitive and Resource Efficient Factored Hybrid HMM Systems are Simpler Than You Think
Tina Raissi, Christoph Lüscher, Moritz Gunz +2
Building competitive hybrid hidden Markov model~(HMM) systems for automatic speech recognition~(ASR) requires a complex multi-stage pipeline consisting of several training criteria…
Improving Long Context Document-Level Machine Translation
Christian Herold, Hermann Ney
Document-level context for neural machine translation (NMT) is crucial to improve the translation consistency and cohesion, the translation of ambiguous inputs, as well as several…
On Search Strategies for Document-Level Neural Machine Translation
Christian Herold, Hermann Ney
Compared to sentence-level systems, document-level neural machine translation (NMT) models produce a more consistent output across a document and are able to better resolve ambigui…
Improving Language Model Integration for Neural Machine Translation
Christian Herold, Yingbo Gao, Mohammad Zeineldeen +1
The integration of language models for neural machine translation has been extensively studied in the past. It has been shown that an external language model, trained on additional…
RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition
Wei Zhou, Eugen Beck, Simon Berger +2
Modern public ASR tools usually provide rich support for training various sequence-to-sequence (S2S) models, but rather simple support for decoding open-vocabulary scenarios only.…
Task-oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10
David Thulke, Nico Daheim, Christian Dugast +1
This paper summarizes our contributions to the document-grounded dialog tasks at the 9th and 10th Dialog System Technology Challenges (DSTC9 and DSTC10). In both iterations the tas…
Analyzing And Improving Neural Speaker Embeddings for ASR
Christoph Lüscher, Jingjing Xu, Mohammad Zeineldeen +2
Neural speaker embeddings encode the speaker's speech characteristics through a DNN model and are prevalent for speaker verification tasks. However, few studies have investigated t…
Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers
Zijian Yang, Wei Zhou, Ralf Schlüter +1
Recently, RNN-Transducers have achieved remarkable results on various automatic speech recognition tasks. However, lattice-free sequence discriminative training methods, which obta…
Does Joint Training Really Help Cascaded Speech Translation?
Viet Anh Khoa Tran, David Thulke, Yingbo Gao +2
Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results. However, fundamental…
Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token
Baohao Liao, David Thulke, Sanjika Hewavitharana +2
The pre-training of masked language models (MLMs) consumes massive computation to achieve good results on downstream NLP tasks, resulting in a large carbon footprint. In the vanill…
Enhancing and Adversarial: Improve ASR with Speaker Labels
Wei Zhou, Haotian Wu, Jingjing Xu +4
ASR can be improved by multi-task learning (MTL) with domain enhancing or domain adversarial training, which are two opposite objectives with the aim to increase/decrease domain va…
Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model
Nico Daheim, David Thulke, Christian Dugast +1
In this work, we present a model for document-grounded response generation in dialog that is decomposed into two components according to Bayes theorem. One component is a tradition…
Monotonic segmental attention for automatic speech recognition
Albert Zeyer, Robin Schmitt, Wei Zhou +2
We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, bette…
Is Encoder-Decoder Redundant for Neural Machine Translation?
Yingbo Gao, Christian Herold, Zijian Yang +1
Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. For machine translation, despite the evolution from long short-term memory networks to Trans…
Revisiting Checkpoint Averaging for Neural Machine Translation
Yingbo Gao, Christian Herold, Zijian Yang +1
Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models. The calculation is cheap to perform and the fact that…
HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch
Tina Raissi, Wei Zhou, Simon Berger +2
In this work, we compare from-scratch sequence-level cross-entropy (full-sum) training of Hidden Markov Model (HMM) and Connectionist Temporal Classification (CTC) topologies for a…
Efficient Utilization of Large Pre-Trained Models for Low Resource ASR
Peter Vieting, Christoph Lüscher, Julian Dierkes +2
Unsupervised representation learning has recently helped automatic speech recognition (ASR) to tackle tasks with limited labeled data. Following this, hardware limitations and appl…
Improving the Training Recipe for a Robust Conformer-based Hybrid Model
Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher +2
Speaker adaptation is important to build robust automatic speech recognition (ASR) systems. In this work, we investigate various methods for speaker adaptive training (SAT) based o…
Efficient Training of Neural Transducer for Speech Recognition
Wei Zhou, Wilfried Michel, Ralf Schlüter +1
As one of the most popular sequence-to-sequence modeling approaches for speech recognition, the RNN-Transducer has achieved evolving performance with more and more sophisticated ne…
Improving Factored Hybrid HMM Acoustic Modeling without State Tying
Tina Raissi, Eugen Beck, Ralf Schlüter +1
In this work, we show that a factored hybrid hidden Markov model (FH-HMM) which is defined without any phonetic state-tying outperforms a state-of-the-art hybrid HMM. The factored…
Adapting Document-Grounded Dialog Systems to Spoken Conversations using Data Augmentation and a Noisy Channel Model
David Thulke, Nico Daheim, Christian Dugast +1
This paper summarizes our submission to Task 2 of the second track of the 10th Dialog System Technology Challenge (DSTC10) "Knowledge-grounded Task-oriented Dialogue Modeling on Sp…
Self-Normalized Importance Sampling for Neural Language Modeling
Zijian Yang, Yingbo Gao, Alexander Gerstenberger +3
To mitigate the problem of having to traverse over the full vocabulary in the softmax normalization of a neural language model, sampling-based training criteria are proposed and in…