检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Zoltan Tuske Ralf Schluter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52056 Aachen Germany

ISBN: (纸本)9781479903573

Hierarchical Multi Layer Perceptron (MLP) based long-term feature extraction is optimized for TANDEM connectionist large vocabulary continuous speech recognition (LVCSR) system within the QUAERO project. Training the bottleneck MLP on multi-resolutional RASTA filtered critical band energies, more than 20% relative word error rate (WER) reduction over standard MFCC system is observed after optimizing the number of target labels. Furthermore, introducing a deeper structure in the hierarchical bottleneck processing the relative gain increases to 25%. The final system based on deep bottleneck TANDEM features clearly outperforms the hybrid approach, even if the long-term features are also presented to the deep MLP acoustic model. The results are also verified on evaluation data of the year 2012, and about 20% relative WER improvement over classical cepstral system is measured even after speaker adaptive training.

关键词： LVCSR MRASTA MLP bottleneck hierarchical deep neural network hybrid TANDEM Traffic Bottlenecks CSRP3 gene Hierarchical HYBRID Tandem relative gain

来源：评论

学校读者我要写书评

暂无评论

ACOUSTIC MODELING OF SPEECH WAVEFORM BASED ON MULTI-RESOLUTION, NEURAL NETWORK SIGNAL PROCESSING

ACOUSTIC MODELING OF SPEECH WAVEFORM BASED ON MULTI-RESOLUTI...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Zoltán Tüske Ralf Schlüter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52056 Aachen Germany

ISBN: (纸本)9781538646595

Recently, several papers have demonstrated that neural networks (NN) are able to perform the feature extraction as part of the acoustic model. Motivated by the Gammatone feature extraction pipeline, in this paper we extend the waveform based NN model by a second level of time-convolutional element. The proposed extension generalizes the envelope extraction block, and allows the model to learn multi-resolutional representations. Automatic speech recognition (ASR) experiments show significant word error rate reduction over our previous best acoustic model trained in the signal domain directly. Although we use only 250 hours of speech, the data-driven NN based speech signal processing performs nearly equally to traditional handcrafted feature extractors. In additional experiments, we also test segment-level feature normalization techniques on NN derived features, which improve the results further. However, the porting of speech representations derived by a feed-forward NN to a LSTM back-end model indicates much less robustness of the NN front-end compared to the standard feature extractors. Analysis of the weights in the proposed new layer reveals that the NN prefers both multi-resolution and modulation spectrum representations.

关键词： ASR neural network time-signal waveform modulation spectrum feature representation modulation spectra waveforms time signal Speech recognition Neural network aquifer storage and recovery Feature extraction Speech signal processing Multi-resolution Acoustic models

来源：评论

学校读者我要写书评

暂无评论

MULTILINGUAL MRASTA FEATURES FOR LOW-RESOURCE KEYWORD SEARCH AND SPEECH recognition SYSTEMS

MULTILINGUAL MRASTA FEATURES FOR LOW-RESOURCE KEYWORD SEARCH...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Zoltan Tuske David Nolden Ralf Schluter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University 52056 Aachen Germany

ISBN: (纸本)9781479928941

This paper investigates the application of hierarchical MRASTA bottleneck (BN) features for under-resourced languages within the IARPA Babel project. Through multilingual training of Multilayer Perceptron (MLP) BN features on five languages (Cantonese, Pashto, Tagalog, Turkish, and Vietnamese), we could end up in a single feature stream which is more beneficial to all languages than the unilingual features. In the case of balanced corpus sizes, the multilingual BN features improve the automatic speech recognition (ASR) performance by 3-5% and the keyword search (KWS) by 3-10% relative for both limited (LLP) and full language packs (FLP). Borrowing orders of magnitude more data from non-target FLPs, the recognition error rate is reduced by 8-10%, and the spoken term detection is improved by over 40% relative on Vietnamese and Pashto LLP. Aiming at the fast development of acoustic models, cross-lingual transfer of multilingually "pretrained" BN features for a new language is also investigated. Without the need of any MLP training on the new language, the ported BN features performed similarly to the unilingual features on FLP and significantly better on LLP. Results also show that a simple fine-tuning step on the new language is enough to achieve comparable KWS and ASR performance to that system where the target language is also involved in the time-consuming multilingual training.

关键词： language Speech recognition Vietnamese Vietnamese Object oriented programming languages fault-location problem KEYWORD Juvenile Spinal Muscular Atrophy Error analysis CSRP3 gene aquifer storage and recovery

来源：评论

学校读者我要写书评

暂无评论

Prediction of LSTM-RNN Full Context States as a Subtask for N-Gram Feedforward language Models

Prediction of LSTM-RNN Full Context States as a Subtask for ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Kazuki Irie Zhihong Lei Ralf Schlüter Hermann Ney Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University D-52056 Aachen Germany

ISBN: (纸本)9781538646595

Long short-term memory (LSTM) recurrent neural network language models compress the full context of variable lengths into a fixed size vector. In this work, we investigate the task of predicting the LSTM hidden representation of the full context from a truncated n-gram context as a subtask for training an n-gram feedforward language model. Since this approach is a form of knowledge distillation, we compare two methods. First, we investigate the standard transfer based on the Kullback-Leibler divergence of the output distribution of the feedforward model from that of the LSTM. Second, we minimize the mean squared error between the hidden state of the LSTM and that of the n-gram feedforward model. We carry out experiments on different subsets of the Switchboard speech recognition dataset for feedforward models with a short (5-gram) and a medium (10-gram) context length. We show that we get improvements in perplexity and word error rate of up to 8% and 4% relative for the medium model, while the improvements are only marginal for the short model.

关键词： language modeling neural networks knowledge distillation student-teacher speech recognition modelling languages Speech recognition FEEDFORWARD Neural network Error analysis

来源：评论

学校读者我要写书评

暂无评论

INVESTIGATION ON CROSS- AND MULTILINGUAL MLP FEATURES UNDER MATCHED AND MISMATCHED ACOUSTICAL CONDITIONS

INVESTIGATION ON CROSS- AND MULTILINGUAL MLP FEATURES UNDER ...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Zoltan Tuske Joel Pinto Daniel Willett Ralf Schluter Human Language Technology and Pattern Recognition Computer Science Department RWTH Aachen University Nuance Communications Deutschland GmbH

ISBN: (纸本)9781479903573

In this paper, Multi Layer Perceptron (MLP) based multilingual bottleneck features are investigated for acoustic modeling in three languages -- German, French, and US English. We use a modified training algorithm to handle the multilingual training scenario without having to explicitly map the phonemes to a common phoneme set. Furthermore, the cross-lingual portability of bottleneck features between the three languages are also investigated. Single pass recognition experiments on large vocabulary SMS dictation task indicate that (1) multilingual bottleneck features yield significantly lower word error rates compared to standard MFCC features (2) multilingual bottleneck features are superior to monolingual bottleneck features trained for the target language with limited training data, and (3) multilingual bottleneck features are beneficial in training acoustic models in a low resource language where only mismatched training data is available - by exploiting the more matched training data from other languages.

关键词： MLP Bottleneck Multilingual Mismatched acoustical condition Traffic Bottlenecks CSRP3 gene Multilingualism Object oriented programming languages language acoustic modeling Training data Phonemes Error analysis

来源：评论

学校读者我要写书评

暂无评论

Development of the 2007 RWTH Mandarin LVCSR system

Development of the 2007 RWTH Mandarin LVCSR system

引用

IEEE Workshop on Automatic Speech recognition and Understanding

作者： Bjorn Hoffmeister Christian Plahl Peter Fritz Georg Heigold Jonas Loof Ralf Schluter Hermann Ney Human Language and Pattern Recognition Computer Science Department 6 RWTH Aachen University Germany

ISBN: (纸本)9781424413690;1424413699

This paper describes the development of the RWTH Mandarin LVCSR system. Different acoustic front-ends together with multiple system cross-adaptation are used in a two stage decoding framework. We describe the system in detail and present systematic recognition results. Especially, we compare a variety of approaches for cross-adapting to multiple systems. During the development we did a comparative study on different methods for integrating tone and phoneme posterior features. Furthermore, we apply lattice based consensus decoding and system combination methods. In these methods, the effect of minimizing character instead of word errors is compared. The final system obtains a character error rate of 17.7% on the GALE 2006 evaluation data.

关键词： Decoding Error analysis Dictionaries Neural networks Natural languages Lattices Vocabulary humans pattern recognition computer science

来源：评论

学校读者我要写书评

暂无评论

Does Joint Training Really Help Cascaded Speech Translation?

arXiv

引用

arXiv 2022年

作者： Tran, Viet Anh Khoa Thulke, David Gao, Yingbo Herold, Christian Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University AachenD-52056 Germany

Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results. However, fundamental challenges such as error propagation from the automatic speech recognition system still remain. To mitigate these problems, recently, people turn their attention to direct data and propose various joint training methods. In this work, we seek to answer the question of whether joint training really helps cascaded speech translation. We review recent papers on the topic and also investigate a joint training criterion by marginalizing the transcription posterior probabilities. Our findings show that a strong cascaded baseline can diminish any improvements obtained using joint training, and we suggest alternatives to joint training. We hope this work can serve as a refresher of the current speech translation landscape, and motivate research in finding more efficient and creative ways to utilize the direct data for speech translation. Copyright © 2022, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Improvements in Dynamic Programming Beam Search for Phrase-based Statistical Machine Translation 5

Improvements in Dynamic Programming Beam Search for Phrase-b...

引用

5th International Workshop on Spoken language Translation, IWSLT 2008

作者： Zens, Richard Ney, Hermann Human Language Technology and Pattern Recognition Lehrstuhl für Informatik 6 Computer Science Department RWTH Aachen University AachenD-52056 Germany Google Inc. 1600 Am-phitheatre Parkway Mountain ViewCA94043 United States

Search is a central component of any statistical machine translation system. We describe the search for phrase-based SMT in detail and show its importance for achieving good translation quality. We introduce an explicit distinction between reordering and lexical hypotheses and organize the pruning accordingly. We show that for the large Chinese-English NIST task already a small number of lexical alternatives is sufficient, whereas a large number of reordering hypotheses is required to achieve good translation quality. The resulting system compares favorably with the current state-of-the-art, in particular we perform a comparison with cube pruning as well as with Moses. © 2008 International Workshop on Spoken language Translation, IWSLT 2008. All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Towards two-dimensional sequence to sequence model in neural machine translation

arXiv

引用

arXiv 2018年

作者： Bahar, Parnia Brix, Christopher Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department Rwth Aachen University AachenD-52056 Germany

This work investigates an alternative model for neural machine translation (NMT) and proposes a novel architecture, where we employ a multi-dimensional long short-term memory (MDLSTM) for translation modeling. In the state-of-the-art methods, source and target sentences are treated as one-dimensional sequences over time, while we view translation as a two-dimensional (2D) mapping using an MDLSTM layer to define the correspondence between source and target words. We extend beyond the current sequence to sequence backbone NMT models to a 2D structure in which the source and target sentences are aligned with each other in a 2D grid. Our proposed topology shows consistent improvements over attention-based sequence to sequence model on two WMT 2017 tasks, German↔English. Copyright © 2018, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture

arXiv

引用

arXiv 2020年

作者： Brix, Christopher Bahar, Parnia Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University AachenD-52056 Germany

Sparse models require less memory for storage and enable a faster inference by reducing the necessary number of FLOPs. This is relevant both for time-critical and on-device computations using neural networks. The stabilized lottery ticket hypothesis states that networks can be pruned after none or few training iterations, using a mask computed based on the unpruned converged model. On the transformer architecture and the WMT 2014 English→German and English→French tasks, we show that stabilized lottery ticket pruning performs similar to magnitude pruning for sparsity levels of up to 85%, and propose a new combination of pruning techniques that outperforms all other techniques for even higher levels of sparsity. Furthermore, we confirm that the parameter’s initial sign and not its specific value is the primary factor for successful training, and show that magnitude pruning cannot be used to find winning lottery tickets. Copyright © 2020, The Authors. All rights reserved.

关键词： Network architecture

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：