检索结果-内蒙古大学图书馆

Comparison between Recurrent Networks and Temporal Convolutional Networks Approaches for Skeleton-Based Action Recognition

引用

SENSORS 2021年第6期21卷 2051-2051页

作者： Nan, Mihai Trascau, Mihai Florea, Adina Magda Iacob, Cezar Catalin Univ Politehn Bucuresti Fac Automat Control & Comp RO-060042 Bucharest Romania

Action recognition plays an important role in various applications such as video monitoring, automatic video indexing, crowd analysis, human-machine interaction, smart homes and personal assistive robotics. In this paper, we propose improvements to some methods for human action recognition from videos that work with data represented in the form of skeleton poses. These methods are based on the most widely used techniques for this problem-Graph Convolutional Networks (GCNs), Temporal Convolutional Networks (TCNs) and Recurrent Neural Networks (RNNs). Initially, the paper explores and compares different ways to extract the most relevant spatial and temporal characteristics for a sequence of frames describing an action. Based on this comparative analysis, we show how a TCN type unit can be extended to work even on the characteristics extracted from the spatial domain. To validate our approach, we test it against a benchmark often used for human action recognition problems and we show that our solution obtains comparable results to the state-of-the-art, but with a significant increase in the inference speed.

关键词： action recognition sequence-to-sequence temporal convolutional networks recurrent networks

来源：评论

学校读者我要写书评

暂无评论

HNSleepNet: A Novel Hybrid Neural Network for Home Health-Care Automatic Sleep Staging with Raw Single-Channel EEG 18

HNSleepNet: A Novel Hybrid Neural Network for Home Health-Ca...

引用

18th IEEE International Conference on Industrial Informatics (INDIN)

作者： Chen, Weiwei Yang, Yun Yang, Po Yunnan Univ Sch Software Kunming Yunnan Peoples R China Univ Sheffield Dept Comp London England

ISBN: (纸本)9781728149646

Proper scoring of sleep stages may offer more intuitive clinical information for assessing the sleep health and improving the diagnosis of sleep disorders in the smart home healthcare. It usually depends on an accurate analysis of the collected physiological signals, especially for the raw sleep Electroencephalogram (EEG). Most of the methods currently available just rely on the pre-processing or handcrafted features that need prior knowledge and preliminary analysis from the sleep experts and only a few of them take full advantage of the temporal information such as the inter-epoch dependency or transition rules among stages, which are more effective for identifying the differences among the sleep stages. In such cases, we proposed a novel hybrid neural network named HNSleepNet. It utilizes a two-branch CNN with multi-scale convolution kernels to capture the time-invariant features from the adjacent sleep EEG epochs both in time and frequency domains automatically, and attention-based residual encoder-decoder LSTM layers to learn the inter- epoch dependency and transition rules at the sequence-wise level. After the two-step training, HNSleepNet can perform sequence-to-sequence automatic sleep staging with a raw single channel EEG in an end-to-end way. As the experimental results demonstrated, its performance achieved a better overall accuracy and macro F1-score (MASS: 88%, 0.85, Sleep-EDF: 87%-80%, 0.79-0.74) compared with the state-of-the-art approaches on various single-channels (F4-EOG (Left), Fpz-Cz and Pz-Oz) in two public datasets with different scoring standards (AASM and R&K), We hope this progress can make clinically practical value in promoting home sleep studies on various home health-care devices.

关键词： Automatic sleep staging Raw single- channel EEG sequence-to-sequence Hybrid neural network Smart home healthcare

来源：评论

学校读者我要写书评

暂无评论

Copy Mechanism and Tailored Training for Character-Based Data-to-Text Generation

Copy Mechanism and Tailored Training for Character-Based Dat...

引用

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Roberti, Marco Bonetta, Giovanni Cancelliere, Rossella Gallinari, Patrick Univ Turin Comp Sci Dept Via Pessinetto 12 I-12149 Turin Italy Sorbonne Univ 4 Pl Jussieu F-75005 Paris France Criteo AI Lab 32 Rue Blanche F-75009 Paris France

ISBN: (纸本)9783030461478;9783030461461

In the last few years, many different methods have been focusing on using deep recurrent neural networks for natural language generation. The most widely used sequence-to-sequence neural methods are word-based: as such, they need a pre-processing step called delexicalization (conversely, relexicalization) to deal with uncommon or unknown words. These forms of processing, however, give rise to models that depend on the vocabulary used and are not completely neural. In this work, we present an end-to-end sequence-to-sequence model with attention mechanism which reads and generates at a character level, no longer requiring delexicalization, tokenization, nor even lowercasing. Moreover, since characters constitute the common "building blocks" of every text, it also allows a more general approach to text generation, enabling the possibility to exploit transfer learning for training. These skills are obtained thanks to two major features: (i) the possibility to alternate between the standard generation mechanism and a copy one, which allows to directly copy input facts to produce outputs, and (ii) the use of an original training pipeline that further improves the quality of the generated texts. We also introduce a new dataset called E2E+, designed to highlight the copying capabilities of character-based models, that is a modified version of the well-known E2E dataset used in the E2E Challenge. We tested our model according to five broadly accepted metrics (including the widely used bleu), showing that it yields competitive performance with respect to both character-based and word-based approaches.

关键词： Natural language processing Data-to-text generation Deep learning sequence-to-sequence Dataset

来源：评论

学校读者我要写书评

暂无评论

Early Stage LM Integration Using Local and Global Log-Linear Combination 21

Early Stage LM Integration Using Local and Global Log-Linear...

引用

Interspeech Conference

作者： Michel, Wilfried Schlueter, Ralf Ney, Hermann Rhein Westfal TH Aachen Comp Sci Dept Human Language Technol & Pattern Recognit D-52056 Aachen Germany AppTek GmbH D-52062 Aachen Germany

ISBN: (纸本)9781713820697

sequence-to-sequence models with an implicit alignment mechanism (e.g. attention) are closing the performance gap towards traditional hybrid hidden Markov models (HMM) for the task of automatic speech recognition. One important factor to improve word error rate in both cases is the use of an external language model (LM) trained on large text-only corpora. Language model integration is straightforward with the clear separation of acoustic model and language model in classical HMM-based modeling. In contrast, multiple integration schemes have been proposed for attention models. In this work, we present a novel method for language model integration into implicit-alignment based sequence-to-sequence models. Log-linear model combination of acoustic and language model is performed with a per-token renormalization. This allows us to compute the full normalization term efficiently both in training and in testing. This is compared to a global renormalization scheme which is equivalent to applying shallow fusion in training. The proposed methods show good improvements over standard model combination (shallow fusion) on our state-of-the-art Librispeech system. Furthermore, the improvements are persistent even if the LM is exchanged for a more powerful one after training.

关键词： sequence-to-sequence language model integration deep fusion shallow fusion

来源：评论

学校读者我要写书评

暂无评论

Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus 20

Asking Questions the Human Way: Scalable Question-Answer Gen...

引用

29th World Wide Web Conference (WWW)

作者： Liu, Bang Wei, Haojie Niu, Di Chen, Haolan He, Yancheng Univ Alberta Edmonton AB Canada Tencent Platform & Content Grp Shenzhen Peoples R China

ISBN: (纸本)9781450370233

The ability to ask questions is important in both human and machine intelligence. Learning to ask questions helps knowledge acquisition, improves question-answering and machine reading comprehension tasks, and helps a chatbot to keep the conversation flowing with a human. Existing question generation models are ineffective at generating a large amount of high-quality question-answer pairs from unstructured text, since given an answer and an input passage, question generation is inherently a one-to-many mapping. In this paper, we propose Answer-Clue-Style-aware Question Generation (ACS-QG), which aims at automatically generating high-quality and diverse question-answer pairs from unlabeled text corpus at scale by imitating the way a hurnat i asks questions. Our system consists of: i) an information extractor, which samples from the text multiple types of assistive information to guide question generation;ii) neural question generators, which generate diverse and controllable questions, leveraging the extracted assistive information;and iii) a neural quality controller, which removes low-quality generated data based on text entailment. We compare our question generation models with existing approaches and resort to voluntary human evaluation to assess the quality of the generated question-answer pairs. The evaluation results suggest that our system dramatically outperforms state-of-the-art neural question generation models in terms of the generation quality, while being scalable in the meantime. With models trained on a relatively smaller amount of data, we can generate 2.8 million quality-assured question-answer pairs from a million sentences found in Wikipedia.

关键词： Question Generation sequence-to-sequence Machine Reading Comprehension

来源：评论

学校读者我要写书评

暂无评论

TRANSFORMER TRANSDUCER: A STREAMABLE SPEECH RECOGNITION MODEL WITH TRANSFORMER ENCODERS AND RNN-T LOSS

TRANSFORMER TRANSDUCER: A STREAMABLE SPEECH RECOGNITION MODE...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Mang, Qian Lu, Han Sak, Hasim Nipathi, Anshuman McDermott, Erik Koo, Stephen Kumar, Shankar Google Inc Mountain View CA 94043 USA

ISBN: (纸本)9781509066315

In this paper we present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks based on self-attention are used to encode both audio and label sequences independently. The activations from both audio and label encoders are combined with a feed-forward layer to compute a probability distribution over the label space for every combination of acoustic frame position and label history. This is similar to the Recurrent Neural Network Transducer (RNN-T) model, which uses RNNs for information encoding instead of Transformer encoders. The model is trained with the RNN-T loss well-suited to streaming decoding. We present results on the LibriSpeech dataset showing that limiting the left context for self-attention in the Transformer layers makes decoding computationally tractable for streaming, with only a slight degradation in accuracy. We also show that the full attention version of our model beats the-state-of-the art accuracy on the LibriSpeech benchmarks. Our results also show that we can bridge the gap between full attention and limited attention versions of our model by attending to a limited number of future frames.

关键词： Transformer RNN-T sequence-to-sequence encoder-decoder end-to-end speech recognition

来源：评论

学校读者我要写书评

暂无评论

RECOApy: Data recording, pre-processing and phonetic transcription for end-to-end speech-based applications 21

RECOApy: Data recording, pre-processing and phonetic transcr...

引用

Interspeech Conference

作者： Stan, Adriana Tech Univ Cluj Napoca Commun Dept Cluj Napoca Romania

ISBN: (纸本)9781713820697

Deep learning enables the development of efficient end-to-end speech processing applications while bypassing the need for expert linguistic and signal processing features. Yet, recent studies show that good quality speech resources and phonetic transcription of the training data can enhance the results of these applications. In this paper, the RECOApy tool is introduced. RECOApy streamlines the steps of data recording and pre-processing required in end-to-end speech-based applications. The tool implements an easy-to-use interface for prompted speech recording, spectrogram and waveform analysis, utterance-level normalisation and silence trimming, as well grapheme-to-phoneme conversion of the prompts in eight languages: Czech, English, French, German, Italian, Polish, Romanian and Spanish. The grapheme-to-phoneme (G2P) converters are deep neural network (DNN) based architectures trained on lexicons extracted from theWiktionary online collaborative resource. With the different degree of orthographic transparency, as well as the varying amount of phonetic entries across the languages, the DNN's hyperparameters are optimised with an evolution strategy. The phoneme and word error rates of the resulting G2P converters are presented and discussed. The tool, the processed phonetic lexicons and trained G2P models are made freely available.

关键词： speech recording tool multilingual phonetic transcription grapheme-to-phoneme evolution strategy sequence-to-sequence convolutional networks transformer networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Automatic Romanian Lemmatization

引用

Procedia Computer Science 2021年 192卷 49-58页

作者： Maria Nuţu Department of Computer Science Faculty of Mathematics and Computer Science Babeş-Bolyai University Cluj-Napoca RO-400084 Communications Department Technical University of Cluj-Napoca RO-400114

This paper proposes a deep learning sequence-to-sequence approach to improve the task of automatic Romanian lemmatization. The study compares 24 systems using different combinations of recurrent, convolutional and attention layers, while the text input consists of word-lemma pairs, both at word and trigram level. As Romanian is a low resourced language in the field of text processing, the aim of this study is to use as little input information as possible. Thus, to increase the lemmatization accuracy, additional lexical features (such as context and POS tags) have been provided only gradually. For the trigrams case, two scenarios were proposed: to predict the lemma for every word from the sequence or to predict the lemma only for the word in the middle. The lemmatizers have been analyzed on two Romanian datasets: the Romanian Explicative Dictionary (DEX) and the belletristic subset of the CoRoLa corpus. For the DEX dataset, the best results were obtained with the LSTM-based systems at both word (99.32%) and character level (99.43%). For the CoRoLa subset, the CNN-based architecture outperforms at trigram (95.86%) and word level (99.09%) while the LSTM-stacked system obtained the highest accuracy at character level (98.78%).

关键词： Lemmatization Part-of-Speech tagging LSTM CNN deep neural networks sequence-to-sequence Romanian

来源：评论

学校读者我要写书评

暂无评论

Forecasting Building Electricity Power Consumption Using Deep Learning Approach

Forecasting Building Electricity Power Consumption Using Dee...

引用

IEEE International Conference on Big Data and Smart Computing (BigComp)

作者： Lee, Young-Jun Choi, Ho-Jin Korea Adv Inst Sci & Technol Sch Comp Daejeon South Korea

ISBN: (纸本)9781728160344

As electricity power usage increases in buildings, it is important to use and supply electricity power efficiently. Recently, there are studies to forecast the energy consumption by using the deep learning method, which can deal with time-series data. In this paper, we compare several deep learning methods to forecast the electricity power consumption in buildings. More specifically, we utilize the vanilla LSTM/GRU with multiple layers, the sequence-to-sequence model, and the sequence-to-sequence model with attention mechanisms. In the experiments, the LSTM/GRU models achieved good overall performance in the RMSE metrics. However, the variations of sequence-to-sequence models showed low performance due to the variation of floating number. Also, in a graphical viewpoint, the LSTM/GRU models well follow the trends of electricity power consumption, but the variation of sequence-to-sequence models can not follow the electricity power consumption pattern well.

关键词： electricity power forecasting deep learning LSTM GRU sequence-to-sequence attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Learning with Data Augmentation for End-to-End ASR 21

Semi-Supervised Learning with Data Augmentation for End-to-E...

引用

Interspeech Conference

作者： Weninger, Felix Mana, Franco Gemello, Roberto Andres-Ferrer, Jesus Zhan, Puming Nuance Commun Inc Burlington MA 01803 USA Nuance Commun Turin Italy Nuance Commun Valencia Spain

ISBN: (纸本)9781713820697

In this paper, we apply Semi-Supervised Learning (SSL) along with Data Augmentation (DA) for improving the accuracy of End-to-End ASR. We focus on the consistency regularization principle, which has been successfully applied to image classification tasks, and present sequence-to-sequence (seq2seq) versions of the FixMatch and Noisy Student algorithms. Specifically, we generate the pseudo labels for the unlabeled data on-the-fly with a seq2seq model after perturbing the input features with DA. We also propose soft label variants of both algorithms to cope with pseudo label errors, showing further performance improvements. We conduct SSL experiments on a conversational speech data set (doctor-patient conversations) with 1.9 kh manually transcribed training data, using only 25% of the original labels (475 h labeled data). In the result, the Noisy Student algorithm with soft labels and consistency regularization achieves 10.4% word error rate (WER) reduction when adding 475 h of unlabeled data, corresponding to a recovery rate of 92 %. Furthermore, when iteratively adding 950 h more unlabeled data, our best SSL performance is within 5% WER increase compared to using the full labeled training set (recovery rate: 78 %).

关键词： automatic speech recognition semi-supervised learning data augmentation sequence-to-sequence end-to-end

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：