检索结果-内蒙古大学图书馆

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Wiesler, Simon Golik, Pavel Schluter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany LIMSI CNRS Spoken Language Processing Group Paris France

ISBN: (纸本)9781467369978

In this paper we present an investigation of sequence-discriminative training of deep neural networks for automatic speech recognition. We evaluate different sequence-discriminative training criteria (MMI and MPE) and optimization algorithms (including SGD and Rprop) using the RASR toolkit. Further, we compare the training of the whole network with that of the output layer only. Technical details necessary for a robust training are studied, since there is no consensus yet on the ultimate training recipe. The investigation extends our previous work on training linear bottleneck networks from scratch showing the consistently positive effect of sequence training. © 2015 IEEE.

关键词： deep neural networks optimization sequence training speech recognition

来源：评论

学校读者我要写书评

暂无评论

Investigation on data adaptation techniques for neural named entity recognition 59

Investigation on data adaptation techniques for neural named...

引用

2021 Student Research Workshop, SRW 2021 at the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural language Processing, ACL-IJCNLP 2021

作者： Tokarchuk, Evgeniia Thulke, David Wang, Weiyue Dugast, Christian Ney, Hermann Informatics Institute University of Amsterdam Netherlands Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Germany

ISBN: (纸本)9781954085558

Data processing is an important step in various natural language processing tasks. As the commonly used datasets in named entity recognition contain only a limited number of samples, it is important to obtain additional labeled data in an efficient and reliable manner. A common practice is to utilize large monolingual unlabeled corpora. Another popular technique is to create synthetic data from the original labeled data (data augmentation). In this work, we investigate the impact of these two methods on the performance of three different named entity recognition tasks. © 2021 Association for Computational Linguistics.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Sequence-discriminative training of recurrent neural networks 40

Sequence-discriminative training of recurrent neural network...

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Voigtlaender, Paul Doetsch, Patrick Wiesler, Simon Schluter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany LIMSI CNRS Spoken Language Processing Group Paris France

ISBN: (纸本)9781467369978

We investigate sequence-discriminative training of long shortterm memory recurrent neural networks using the maximum mutual information criterion. We show that although recurrent neural networks already make use of the whole observation sequence and are able to incorporate more contextual information than feed forward networks, their performance can be improved with sequence-discriminative training. Experiments are performed on two publicly available handwriting recognition tasks containing English and French handwriting. On the English corpus, we obtain a relative improvement in WER of over 11% with maximum mutual information (MMI) training compared to cross-entropy training. On the French corpus, we observed that it is necessary to interpolate the MMI objective function with cross-entropy. © 2015 IEEE.

关键词： handwriting recognition long shortterm memory recurrent neural networks sequence-discriminative training

来源：评论

学校读者我要写书评

暂无评论

Feature-rich sub-lexical language models using a maximum entropy approach for German LVCSR

Feature-rich sub-lexical language models using a maximum ent...

引用

14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013

作者： Shaik, M. Ali Basha El-Desoky Mousa, Amr Schlüter, Ralf Ney, Hermann Computer Science Department Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany Spoken Language Processing Group LIMSI CNRS Paris France

German is a morphologically rich language having a high degree of word inflections, derivations and compounding. This leads to high out-of-vocabulary (OOV) rates and poor language model (LM) probabilities in the large vocabulary continuous speech recognition (LVCSR) systems. One of the main challenges in the German LVCSR is the recognition of the OOV words. For this purpose, data-driven morphemes are used to provide higher lexical coverage. On the other hand, the probability estimates of a sub-lexical LM could be further improved using feature-rich LMs like maximum entropy (MaxEnt) and class-based LMs. In this work, for a sub-lexical level German LVCSR task, we investigate the use of the multiple morpheme level features as classes for building class-based LMs that are estimated using the state-of-the-art MaxEnt approach. Thus, the benefits of both the MaxEnt LMs and the traditional class-based LMs are effectively combined. Furthermore, we experiment the use of Maximum a-posteriori adaptation over the MaxEnt class-based LMs. We show consistent reductions in both the OOV recognition error rate and the word error rate (WER) on a German LVCSR task from the Quaero project, compared to the traditional class-based and the N-gram morpheme based LM. Copyright © 2013 ISCA.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Morpheme level hierarchical pitman-Yor class-based language models for LVCSR of morphologically rich languages

Morpheme level hierarchical pitman-Yor class-based language ...

引用

14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013

作者： El-Desoky Mousa, Amr Shaik, M. Ali Basha Schlüter, Ralf Ney, Hermann Computer Science Department Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany Spoken Language Processing Group LIMSI CNRS Paris France

Performing large vocabulary continuous speech recognition (LVCSR) for morphologically rich languages is considered a challenging task. The morphological richness of such languages leads to high out-of-vocabulary (OOV) rates and poor language model (LM) probabilities. In this case, the use of morphemes has been shown to increase the lexical coverage and lower the LM perplexity. Another approach used to improve the LM probability estimates is to incorporate additional knowledge sources in the LM estimation process using classbased LMs (CLMs). Recently, the hierarchical Pitman-Yor LMs (HPYLMs) have shown superiority over the modified Kneser- Ney (MKN) smoothed N-gram LMs in terms of both perplexity (PPL) and word error rate (WER) on word-based LVCSR tasks. In this paper, hierarchical Pitman-Yor class-based LMs (HPYCLMs) are combined with morpheme level language modeling. This enables the application of the proposed models on top of morpheme-based systems. Experiments are conducted on Arabic and German LVCSR tasks. Consistent performance improvements are obtained for all the available corpora compared to the conventional morpheme-based and class-based LMs. Copyright © 2013 ISCA.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

RWTHLM - The RWTH Aachen University neural network language modeling toolkit 15

RWTHLM - The RWTH Aachen University neural network language ...

引用

15th Annual Conference of the International Speech Communication Association: Celebrating the Diversity of Spoken languages, INTERSPEECH 2014

作者： Sundermeyer, Martin Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany Spoken Language Processing Group LIMSI CNRS Paris France

We present a novel toolkit that implements the long short-term memory (LSTM) neural network concept for language modeling. The main goal is to provide a software which is easy to use, and which allows fast training of standard recurrent and LSTM neural network language models. The toolkit obtains state-of-the-art performance on the standard Treebank corpus. To reduce the training time, BLAS and related libraries are supported, and it is possible to evaluate multiple word sequences in parallel. In addition, arbitrary word classes can be used to speed up the computation in case of large vocabulary sizes. Finally, the software allows easy integration with SRILM, and it supports direct decoding and rescoring of HTK lattices. The toolkit is available for download under an open source license. Copyright © 2014 ISCA.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables 40

Integrating Gaussian mixtures into deep neural networks: Sof...

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Tuske, Zoltan Tahir, Muhammad Ali Schluter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Aachen Germany Spoken Language Processing Group LIMSI CNRS Paris France

ISBN: (纸本)9781467369978

In the hybrid approach, neural network output directly serves as hidden Markov model (HMM) state posterior probability estimates. In contrast to this, in the tandem approach neural network output is used as input features to improve classic Gaussian mixture model (GMM) based emission probability estimates. This paper shows that GMM can be easily integrated into the deep neural network framework. By exploiting its equivalence with the log-linear mixture model (LMM), GMM can be transformed to a large softmax layer followed by a summation pooling layer. Theoretical and experimental results indicate that the jointly trained and optimally chosen GMM and bottleneck tandem features cannot perform worse than a hybrid model. Thus, the question 'hybrid vs. tandem' simplifies to optimizing the output layer of a neural network. Speech recognition experiments are carried out on a broadcast news and conversations task using up to 12 feed-forward hidden layers with sigmoid and rectified linear unit activation functions. The evaluation of the LMM layer shows recognition gains over the classic softmax output. © 2015 IEEE.

关键词： ASR bottleneck DNN GMM hybrid LMM Log-linear mixture model neural network tandem

来源：评论

学校读者我要写书评

暂无评论

Skin-color based videos categorization

引用

International Journal of computer science Issues 2012年第1 1-3期9卷 473-477页

作者： Khan, Rehanullah Maqsood, Asad Khan, Zeeshan Ishaq, Muhammad Arif, Arsalan Sarhad University of Science and Information Technology Peshawar Pakistan RWTH Aachen Human Language Technology and Pattern Recognition Peshawar Pakistan UET Mardan Peshawar Pakistan

On dedicated websites, people can upload videos and share it with the rest of the world. Currently these videos are categorized manually by the help of the user community. In this paper, we propose a combination of color spaces with the Bayesian network approach for robust detection of skin color followed by an automated video categorization. Experimental results show that our method can achieve satisfactory performance for categorizing videos based on skin color. © 2012 International Journal of computer science Issues.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing and Adversarial: Improve ASR with Speaker Labels 48

Enhancing and Adversarial: Improve ASR with Speaker Labels

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

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

ISBN: (纸本)9781728163277

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. © 2023 IEEE.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers 48

Lattice-Free Sequence Discriminative Training for Phoneme-Ba...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

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

ISBN: (纸本)9781728163277

Recently, RNN-Transducers have achieved remarkable results on various automatic speech recognition tasks. However, lattice-free sequence discriminative training methods, which obtain superior performance in hybrid models, are rarely investigated in RNN-Transducers. In this work, we propose three lattice-free training objectives, namely lattice-free maximum mutual information, lattice-free segment-level minimum Bayes risk, and lattice-free minimum Bayes risk, which are used for the final posterior output of the phoneme-based neural transducer with a limited context dependency. Compared to criteria using N-best lists, lattice-free methods eliminate the decoding step for hypotheses generation during training, which leads to more efficient training. Experimental results show that lattice-free methods gain up to 6.5% relative improvement in word error rate compared to a sequence-level cross-entropy trained model. Compared to the N-best-list based minimum Bayes risk objectives, lattice-free methods gain 40% - 70% relative training time speedup with a small degradation in performance. © 2023 IEEE.

关键词： neural transducer sequence discriminative training Speech recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：