检索结果-内蒙古大学图书馆

EFFICIENT SEQUENCE TRAINING OF ATTENTION MODELS USING APPROXIMATIVE RECOMBINATION

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wynands, Nils-Philipp Michel, Wilfried Rosendahl, Jan Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52062 Germany AppTek GmbH Aachen52062 Germany

Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice. Current state-of-the-art systems with unlimited label context circumvent this problem by limiting the summation to an n-best list of relevant competing hypotheses obtained from beam search. This work proposes to perform (approximative) recombinations of hypotheses during beam search, if they share a common local history. The error that is incurred by the approximation is analyzed and it is shown that using this technique the effective beam size can be increased by several orders of magnitude without significantly increasing the computational requirements. Lastly, it is shown that this technique can be used to effectively perform sequence discriminative training for attention-based encoder-decoder acoustic models on the LibriSpeech task. Copyright © 2021, The Authors. All rights reserved.

关键词： Speech recognition

RWTH ASR Systems for LibriSpeech: Hybrid vs Attention - w/o Data Augmentation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Lüscher, Christoph Beck, Eugen Irie, Kazuki Kitza, Markus Michel, Wilfried Zeyer, Albert Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

We present state-of-the-art automatic speech recognition (ASR) systems employing a standard hybrid DNN/HMM architecture compared to an attention-based encoder-decoder design for the LibriSpeech task. Detailed descriptions of the system development, including model design, pretraining schemes, training schedules, and optimization approaches are provided for both system architectures. Both hybrid DNN/HMM and attention-based systems employ bi-directional LSTMs for acoustic modeling/encoding. For language modeling, we employ both LSTM and Transformer based architectures. All our systems are built using RWTH’s open-source toolkits RASR and RETURNN. To the best knowledge of the authors, the results obtained when training on the full LibriSpeech training set, are the best published currently, both for the hybrid DNN/HMM and the attention-based systems. Our single hybrid system even outperforms previous results obtained from combining eight single systems. Our comparison shows that on the LibriSpeech 960h task, the hybrid DNN/HMM system outperforms the attention-based system by 15% relative on the clean and 40% relative on the other test sets in terms of word error rate. Moreover, experiments on a reduced 100h-subset of the LibriSpeech training corpus even show a more pronounced margin between the hybrid DNN/HMM and attention-based architectures. Copyright © 2019, The Authors. All rights reserved.

关键词： Hybrid systems

A new training pipeline for an improved neural transducer

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zeyer, Albert Merboldt, André Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52062 Germany AppTek GmbH Aachen52062 Germany

The RNN transducer is a promising end-to-end model candidate. We compare the original training criterion with the full marginalization over all alignments, to the commonly used maximum approximation, which simplifies, improves and speeds up our training. We also generalize from the original neural network model and study more powerful models, made possible due to the maximum approximation. We further generalize the output label topology to cover RNN-T, RNA and CTC. We perform several studies among all these aspects, including a study on the effect of external alignments. We find that the transducer model generalizes much better on longer sequences than the attention model. Our final transducer model outperforms our attention model on Switchboard 300h by over 6% relative WER. Copyright © 2020, The Authors. All rights reserved.

关键词： RNA

MLLP-UPV and RWTH Aachen Spanish ASR Systems for the IberSpeech-RTVE 2018 Speech-to-Text Transcription Challenge 4

学校读者我要写书评

暂无评论

MLLP-UPV and RWTH Aachen Spanish ASR Systems for the IberSpe...

4th International Conference on Advances in Speech and language Technologies for Iberian languages, IberSPEECH 2018

作者： Jorge, Javier Martínez-Villaronga, Adrià Golik, Pavel Giménez, Adrià Silvestre-Cerdà, Joan Albert Doetsch, Patrick Císcar, Vicent Andreu Ney, Hermann Juan, Alfons Sanchis, Albert Departament de Sistemes Informàtics i Computació Universitat Politècnica de València Spain Human Language Technology and Pattern Recognition RWTH Aachen University Germany Escola Tècnica Superior d'Enginyeria Informàtica Universitat Politècnica de València Spain

This paper describes the Automatic Speech recognition systems built by the MLLP research group of Universitat Politècnica de València and the HLTPR research group of RWTH Aachen for the IberSpeech-RTVE 2018 Speech-to-Text Transcription Challenge. We participated in both the closed and the open training conditions. The best system built for the closed condition was an hybrid BLSTM-HMM ASR system using one-pass decoding with a combination of a RNN LM and show-adapted n-gram LMs. It was trained on a set of reliable speech data extracted from the train and dev1 sets using MLLP's transLectures-UPV toolkit (TLK) and TensorFlow. This system achieved 20.0% WER on the dev2 set. For the open condition we used approx. 3800 hours of outof- domain training data from multiple sources and trained a one-pass hybrid BLSTM-HMM ASR system using open-source tools RASR and RETURNN developed at RWTH Aachen. This system scored 15.6% WER on the dev2 set. The highlights of these systems include robust speech data filtering for acoustic model training and show-specific language modeling. © 4th International Conference, IberSPEECH 2018.

关键词： Modeling languages

ON THE RELATION BETWEEN INTERNAL language MODEL AND SEQUENCE DISCRIMINATIVE TRAINING FOR NEURAL TRANSDUCERS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Zijian Zhou, Wei Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

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. In this work, we show that sequence discriminative training has a strong correlation with ILM subtraction from both theoretical and empirical points of view. Theoretically, we derive that the global optimum of maximum mutual information (MMI) training shares a similar formula as ILM subtraction. Empirically, we show that ILM subtraction and sequence discriminative training achieve similar effects across a wide range of experiments on Librispeech, including both MMI and minimum Bayes risk (MBR) criteria, as well as neural transducers and LMs of both full and limited context. The benefit of ILM subtraction also becomes much smaller after sequence discriminative training. We also provide an in-depth study to show that sequence discriminative training has a minimal effect on the commonly used zero-encoder ILM estimation, but a joint effect on both encoder and prediction + joint network for posterior probability reshaping including both ILM and blank suppression. Copyright © 2023, The Authors. All rights reserved.

关键词： Transducers

Generating synthetic audio data for attention-based speech recognition systems

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Rossenbach, Nick Zeyer, Albert Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Germany AppTek GmbH 52074 Aachen Aachen52062 Germany

Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recognition (ASR) systems with synthetic audio generated by a TTS system trained only on the ASR corpora itself. ASR and TTS systems are built separately to show that text-only data can be used to enhance existing end-to-end ASR systems without the necessity of parameter or architecture changes. We compare our method with language model integration of the same text data and with simple data augmentation methods like SpecAugment and show that performance improvements are mostly independent. We achieve improvements of up to 33% relative in word-error-rate (WER) over a strong baseline with data-augmentation in a low-resource environment (LibriSpeech-100h), closing the gap to a comparable oracle experiment by more than 50%. We also show improvements of up to 5% relative WER over our most recent ASR baseline on LibriSpeech-960h. Copyright © 2019, The Authors. All rights reserved.

关键词： Speech synthesis

On language model integration for RNN transducer based speech recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Wei Zheng, Zuoyun Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

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 remove this sequence prior as ILM correction. In this work, we study various ILM correction-based LM integration methods formulated in a common RNN-T framework. We provide a decoding interpretation on two major reasons for performance improvement with ILM correction, which is further experimentally verified with detailed analysis. We also propose an exact-ILM training framework by extending the proof given in the hybrid autoregressive transducer, which enables a theoretical justification for other ILM approaches. Systematic comparison is conducted for both in-domain and cross-domain evaluation on the Librispeech and TED-LIUM Release 2 corpora, respectively. Our proposed exact-ILM training can further improve the best ILM method. Copyright © 2021, The Authors. All rights reserved.

关键词： Transducers

ENHANCING AND ADVERSARIAL: IMPROVE ASR WITH SPEAKER LABELS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhou, Wei Wu, Haotian Xu, Jingjing Zeineldeen, Mohammad Lüscher, Christoph Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

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 variance towards domain-aware/agnostic ASR, respectively. In this work, we study how to best apply these two opposite objectives with speaker labels to improve conformer-based ASR. We also propose a novel adaptive gradient reversal layer for stable and effective adversarial training without tuning effort. Detailed analysis and experimental verification are conducted to show the optimal positions in the ASR neural network (NN) to apply speaker enhancing and adversarial training. We also explore their combination for further improvement, achieving the same performance as i-vectors plus adversarial training. Our best speaker-based MTL achieves 7% relative improvement on the Switchboard Hub5’00 set. We also investigate the effect of such speaker-based MTL w.r.t. cleaner dataset and weaker ASR NN. Copyright © 2022, The Authors. All rights reserved.

关键词： Linearization

Equivalence of segmental and neural transducer modeling: A proof of concept

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Wei Zeyer, Albert Merboldt, André Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen52074 Germany AppTek GmbH Aachen52062 Germany

With the advent of direct models in automatic speech recognition (ASR), the formerly prevalent frame-wise acoustic modeling based on hidden Markov models (HMM) diversified into a number of modeling architectures like encoder-decoder attention models, transducer models and segmental models (direct HMM). While transducer models stay with a frame-level model definition, segmental models are defined on the level of label segments directly. While (soft-)attention-based models avoid explicit alignment, transducer and segmental approach internally do model alignment, either by segment hypotheses or, more implicitly, by emitting so-called blank symbols. In this work, we prove that the widely used class of RNN-Transducer models and segmental models (direct HMM) are equivalent and therefore show equal modeling power. It is shown that blank probabilities translate into segment length probabilities and vice versa. In addition, we provide initial experiments investigating decoding and beam-pruning, comparing time-synchronous and label-/segment-synchronous search strategies and their properties using the same underlying model. Copyright © 2021, The Authors. All rights reserved.

关键词： Transducers