检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Raissi, Tina Zhou, Wei Berger, Simon Schlüter, Ralf Ney, Hermann Human Language Technology and Pattern Recognition Group Rwth Aachen University Germany AppTek GmbH Aachen Germany

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 automatic speech recognition (ASR). Besides accuracy, we further analyze their capability for generating high-quality time alignment between the speech signal and the transcription, which can be crucial for many subsequent applications. Moreover, we propose several methods to improve convergence of from-scratch full-sum training by addressing the alignment modeling issue. Systematic comparison is conducted on both Switchboard and LibriSpeech corpora across CTC, posterior HMM with and w/o transition probabilities, and standard hybrid HMM. We also provide a detailed analysis of both Viterbi forced-alignment and Baum-Welch full-sum occupation probabilities. Copyright © 2022, The Authors. All rights reserved.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Efficient retrieval augmented generation from unstructured knowledge for task-oriented dialog

arXiv

引用

arXiv 2021年

作者： Thulke, David Daheim, Nico Dugast, Christian Ney, Hermann Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany AppTek GmbH Aachen Germany

This paper summarizes our work on the first track of the ninth Dialog System technology Challenge (DSTC 9), "Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access". The goal of the task is to generate responses to user turns in a task-oriented dialog that require knowledge from unstructured documents. The task is divided into three subtasks: detection, selection and generation. In order to be compute efficient, we formulate the selection problem in terms of hierarchical classification steps. We achieve our best results with this model. Alternatively, we employ siamese sequence embedding models, referred to as Dense Knowledge Retrieval, to retrieve relevant documents. This method further reduces the computation time by a factor of more than 100x at the cost of degradation in R@1 of 5-6% compared to the first model. Then for either approach, we use Retrieval Augmented Generation to generate responses based on multiple selected snippets and we show how the method can be used to fine-tune trained embeddings. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

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

A Comparison of Transformer and LSTM Encoder Decoder Models for ASR

A Comparison of Transformer and LSTM Encoder Decoder Models ...

引用

IEEE Workshop on Automatic Speech Recognition and Understanding

作者： Albert Zeyer Parnia Bahar Kazuki Irie Ralf Schlüter Hermann Ney AppTek GmbH Aachen Germany Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany

ISBN: (数字)9781728103068

ISBN: (纸本)9781728103075

We present competitive results using a Transformer encoder-decoder-attention model for end-to-end speech recognition needing less training time compared to a similarly performing LSTM model. We observe that the Transformer training is in general more stable compared to the LSTM, although it also seems to overfit more, and thus shows more problems with generalization. We also find that two initial LSTM layers in the Transformer encoder provide a much better positional encoding. Data-augmentation, a variant of SpecAugment, helps to improve both the Transformer by 33% and the LSTM by 15% relative. We analyze several pretraining and scheduling schemes, which is crucial for both the Transformer and the LSTM models. We improve our LSTM model by additional convolutional layers. We perform our experiments on Lib-riSpeech 1000h, Switchboard 300h and TED-LIUM-v2 200h, and we show state-of-the-art performance on TED-LIUM-v2 for attention based end-to-end models. We deliberately limit the training on LibriSpeech to 12.5 epochs of the training data for comparisons, to keep the results of practical interest, although we show that longer training time still improves more. We publish all the code and setups to run our experiments.

关键词： Decoding Hidden Markov models Training Convergence Encoding Convolutional codes Data models

来源：评论

学校读者我要写书评

暂无评论

Bagging by design for continuous Handwriting Recognition using multi-objective particle swarm optimization

Bagging by design for continuous Handwriting Recognition usi...

引用

International Conference on Document Analysis and Recognition

作者： Mahdi Hamdani Patrick Doetsch Hermann Ney Human Language Technology and Pattern Recognition Group - RWTH Aachen University Germany Spoken Language Processing Group LIMSI CNRS Paris France

Multiple classifier systems are used to improve baseline results using different strategies. Bagging by design improves standard bagging by the minimization of intersection between the different ensembles. This work proposes the use of design bagging for continuous handwriting recognition. The design is performed using a multi-objective particle swarm optimizer. Hidden Markov Models and Long-Short Term Memory Recurrent Neural Networks are used to validate the proposed design. Experiments on English and French Handwriting Recognition with different setups show significant improvements.

关键词： Lattices Optimization Optical character recognition software

来源：评论

学校读者我要写书评

暂无评论

Task-oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10

arXiv

引用

arXiv 2023年

作者： Thulke, David Daheim, Nico Dugast, Christian Ney, Hermann Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany AppTek GmbH Aachen Germany

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 task consists of three subtasks: first detect whether the current turn is knowledge seeking, second select a relevant knowledge document, and third generate a response grounded on the selected document. For DSTC9 we proposed different approaches to make the selection task more efficient. The best method, Hierarchical Selection, actually improves the results compared to the original baseline and gives a speedup of 24x. In the DSTC10 iteration of the task, the challenge was to adapt systems trained on written dialogs to perform well on noisy automatic speech recognition transcripts. Therefore, we proposed data augmentation techniques to increase the robustness of the models as well as methods to adapt the style of generated responses to fit well into the proceeding dialog. Additionally, we proposed a noisy channel model that allows for increasing the factuality of the generated responses. In addition to summarizing our previous contributions, in this work, we also report on a few small improvements and reconsider the automatic evaluation metrics for the generation task which have shown a low correlation to human judgments. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

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

Cascaded span extraction and response generation for document-grounded dialog

arXiv

引用

arXiv 2021年

作者： Daheim, Nico Thulke, David Dugast, Christian Ney, Hermann Human Language Technology and Pattern Recognition Group RWTH Aachen University Germany AppTek GmbH Aachen Germany

This paper summarizes our entries to both subtasks of the first DialDoc shared task which focuses on the agent response prediction task in goal-oriented document-grounded dialogs. The task is split into two subtasks: predicting a span in a document that grounds an agent turn and generating an agent response based on a dialog and grounding document. In the first subtask, we restrict the set of valid spans to the ones defined in the dataset, use a biaffine classifier to model spans, and finally use an ensemble of different models. For the second subtask, we use a cascaded model which grounds the response prediction on the predicted span instead of the full document. With these approaches, we obtain significant improvements in both subtasks compared to the baseline. Copyright © 2021, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures

Comparing the Benefit of Synthetic Training Data for Various...

引用

IEEE Workshop on Automatic Speech Recognition and Understanding

作者： Nick Rossenbach Mohammad Zeineldeen Benedikt Hilmes Ralf Schlüter Hermann Ney Human Language Technology and Pattern Recognition RWTH Aachen University Aachen Germany AppTek GmbH Aachen Germany

ISBN: (纸本)9781665437400

Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle this issue is to generate synthetic data with a trained text-to-speech system (TTS) if additional text is available. This was successfully applied in many publications with AED systems, but only very limited in the context of other ASR architectures. We investigate the effect of varying pre-processing, the speaker embedding and input encoding of the TTS system w.r.t. the effectiveness of the synthesized data for AED-ASR training. Additionally, we also consider internal language model subtraction for the first time, resulting in up to 38% relative improvement. We compare the AED results to a state-of-the-art hybrid ASR system, a monophone based system using connectionist-temporal-classification (CTC) and a monotonic transducer based system. We show that for the later systems the addition of synthetic data has no relevant effect, but they still outperform the AED systems on LibriSpeech-100h. We achieve a final word-error-rate of 3.3%/10.0% with a hybrid system on the clean/noisy test-sets, surpassing any previous state-of-the-art systems on Librispeech-100h that do not include unlabeled audio data.

关键词： Training Transducers Conferences Training data Stability analysis Data models Robustness

来源：评论

学校读者我要写书评

暂无评论

Sign language Gesture Classification Using Neural Networks 4

Sign Language Gesture Classification Using Neural Networks

引用

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

作者： Parcheta, Zuzanna Martínez-Hinarejos, Carlos-D. Sciling S.L. Carrer del Riu 321 Pinedo 46012 Spain Pattern Recognition and Human Language Technology Research Center Universitat Politècnica de València Camino de Vera s/n 46022 Spain

Recent studies have demonstrated the power of neural networks for different fields of artificial intelligence. In most fields, such as machine translation or speech recognition, neural networks outperform previously used methods (Hidden Markov Models with Gaussian Mixtures, Statistical Machine Translation, etc.). In this paper, the efficiency of the LeNet convolutional neural network for isolated word sign language recognition is demonstrated. As a preprocessing step, we apply several techniques to obtain the same dimension for the input that contains gesture information. The performance of these preprocessing techniques on a Spanish Sign language dataset is evaluated. These approaches outperform previously obtained results based on Hidden Markov Models. © 4th International Conference, IberSPEECH 2018.

关键词： Gesture 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：