检索结果-内蒙古大学图书馆

Adversarial training and decoding strategies for end-to-end neural conversation models

COMPUTER SPEECH AND LANGUAGE 2019年 54卷 122-139页

作者： Hori, Takaaki Wang, Wen Koji, Yusuke Hori, Chiori Harsham, Bret Hershey, John R. Mitsubishi Elect Res Labs Cambridge MA 02139 USA Mitsubishi Electr Corp Informat Technol R&D Ctr Kamakura Kanagawa Japan

This paper presents adversarial training and decoding methods for neural conversation models that can generate natural responses given dialog contexts. In our prior work, we built several end-to-end conversation systems for the 6th Dialog System Technology Challenges (DSTC6) Twitter help-desk dialog task. These systems included novel extensions of sequence adversarial training, example-based response extraction, and Minimum Bayes-Risk based system combination. In DSTC6, our systems achieved the best performance in most objective measures such as BLEU and METEOR scores and decent performance in a subjective measure based on human rating. In this paper, we provide a complete set of our experiments for DSTC6 and further extend the training and decoding strategies more focusing on improving the subjective measure, where we combine responses of three adversarial models. Experimental results demonstrate that the extended methods improve the human rating score and outperform the best score in DSTC6. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Dialog system Conversation model sequence-to-sequence model Sentence generation

来源：评论

学校读者我要写书评

暂无评论

Document Summarization model Based on General Context in RNN

引用

JOURNAL OF INFORMATION PROCESSING SYSTEMS 2019年第6期15卷 1378-1391页

作者： Kim, Heechan Lee, Soowon Soongsil Univ Dept Software Convergence Seoul South Korea Soongsil Univ Sch Software Seoul South Korea

In recent years, automatic document summarization has been widely studied in the field of natural language processing thanks to the remarkable developments made using deep learning models. To decode a word, existing models for abstractive summarization usually represent the context of a document using the weighted hidden states of each input word when they decode it. Because the weights change at each decoding step, these weights reflect only the local context of a document. Therefore, it is difficult to generate a summary that reflects the overall context of a document. To solve this problem, we introduce the notion of a general context and propose a model for summarization based on it. The general context reflects overall context of the document that is independent of each decoding step. Experimental results using the CNN/Daily Mail dataset show that the proposed model outperforms existing models.

关键词： Document Summarization General Context Natural Language Processing sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

A sequence-to-sequence Deep Learning Architecture Based on Bidirectional GRU for Type Recognition and Time Location of Combined Power Quality Disturbance

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2019年第8期15卷 4481-4493页

作者： Deng, Yaping Wang, Lu Jia, Hao Tong, Xiangqian Li, Feng Xian Univ Technol Dept Elect Engn Xian 710048 Shaanxi Peoples R China Ningxia Elect Power Res Inst Yinchuan 750011 Peoples R China

In this paper, a sequence-to-sequence deep learning architecture based on the bidirectional gated recurrent unit (Bi-GRU) for type recognition and time location of combined power quality disturbance is proposed. Especially, the proposed methodology can determine the type of each element in input sequence, which is different from existing sequence-to-sequence model employing encoderdecoder network. First, the input sequence is normalized and batched. Second, deep features are extracted frominput sequence by constructing Bi-GRU recurrent neural network, where multiple Bi-GRU layers are stacked together in both forward direction and backward direction. Third, according to aforementioned extracted features, fully connected layer and Softmax are employed to calculate the corresponding probability indicating the category that each element in input sequence is classified to. Fourth, Argmax or Top_K operation is further integrated to determine the type of each element in input sequence by selecting the maximal probability. Finally, the type is recognized, and meanwhile, starting-ending times of disturbances are also located just at the moment when the type is changed. The proposed model is further validated and tested by synthetic signals and practical field signals, respectively. Experimental results demonstrate that the accuracy of type recognition is over 98% for 96 kinds of disturbances including single and combined disturbances with signal-to-noise ration being 20 dB. Besides, the starting-ending times are also located with the absolute error less than six sampling points when sampling frequency is 256 points per cycle with noisy environment.

关键词： Bidirectional gated recurrent unit (Bi-GRU) deep learning power quality disturbance (PQD) sequence-to-sequence model time location type recognition

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based household electric energy consumption forecasting

引用

JOURNAL OF ENGINEERING-JOE 2020年第13期2020卷 639-642页

作者： Hyeon, Jonghwan Lee, HyeYoung Ko, Bowon Choi, Ho-Jin Korea Adv Inst Sci & Technol Sch Comp Daejeon South Korea

With the advent of various electronic products, the household electric energy consumption is continuously increasing, and therefore it becomes very important to predict the household electric energy consumption accurately. Energy prediction models also have been developed for decades with advanced machine learning technologies. Meanwhile, the deep learning models are still actively under study, and many newer models show the state-of-the-art performance. Therefore, it would be meaningful to conduct the same experiment with these new models. Here, the authors predict the household electric energy consumption using deep learning models, known to be suitable for dealing with time-series data. Specifically, vanilla long short-term memory (LSTM), sequence to sequence, and sequence to sequence with attention mechanism are used to predict the electric energy consumption in the household. As a result, the vanilla LSTM shows the best performance on the root-mean-square error metric. However, from a graphical point of view, it seems that the sequence-to-sequence model predicts the energy consumption patterns best and the vanilla LSTM does not follow the pattern well. Also, to achieve the best performance of each deep learning model, vanilla LSTM, sequence to sequence, and sequence to sequence with attention mechanism should observe past 72, 72, and 24 h, respectively.

关键词： power consumption time series learning (artificial intelligence) mean square error methods load forecasting power engineering computing recurrent neural nets vanilla LSTM deep learning model energy prediction models advanced machine learning technologies sequence-to-sequence model energy consumption patterns household electric energy consumption forecasting time-series data vanilla long short-term memory root-mean-square error metric sequence to sequence with attention mechanism time 72 0 hour time 24 0 hour

来源：评论

学校读者我要写书评

暂无评论

sequence-to-sequence models Can Directly Translate Foreign Speech 18

Sequence-to-Sequence Models Can Directly Translate Foreign S...

引用

18th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2017)

作者： Weiss, Ron J. Chorowski, Jan Jaitly, Navdeep Wu, Yonghui Chen, Zhifeng Google Brain Mountain View CA 94043 USA Nvidia Santa Clara CA USA

ISBN: (纸本)9781510848764

We present a recurrent encoder-decoder deep neural network architecture that directly translates speech in one language into text in another. The model does not explicitly transcribe the speech into text in the source language. nor does it require supervision from the ground truth source language transcription during training. We apply a slightly modified sequence-to-sequence with attention architecture that has previously been used for speech recognition and show that it can be repurposed for this more complex task, illustrating the power of attention-based models. A single model trained end-to-end obtains state-of-the-art performance on the Fisher Callhome Spanish-English speech translation task, outperforming a cascade of independently trained sequence-to-sequence speech recognition and machine translation models by 1.8 BLEU points on the Fisher test set. In addition, we find that making use of the training data in both languages by multi-task training sequence-to-sequence speech translation and recognition models with a shared encoder network can improve performance by a further 1.4 BLEU points.

关键词： speech translation sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Parrotron: An End-to-End Speech-to-Speech Conversion model and its Applications to Hearing-Impaired Speech and Speech Separation 20

Parrotron: An End-to-End Speech-to-Speech Conversion Model a...

引用

Interspeech Conference

作者： Biadsy, Fadi Weiss, Ron J. Moreno, Pedro J. Kanvesky, Dimitri Jia, Ye Google Mountain View CA 94043 USA

We describe Parrotron, an end-to-end-trained speech-to-speech conversion model that maps an input spectrogram directly to another spectrogram, without utilizing any intermediate discrete representation. The network is composed of an encoder, spectrogram and phoneme decoders, followed by a vocoder to synthesize a time-domain waveform. We demonstrate that this model can be trained to normalize speech from any speaker regardless of accent, prosody, and background noise, into the voice of a single canonical target speaker with a fixed accent and consistent articulation and prosody. We further show that this normalization model can be adapted to normalize highly atypical speech from a deaf speaker, resulting in significant improvements in intelligibility and naturalness, measured via a speech recognizer and listening tests. Finally, demonstrating the utility of this model on other speech tasks, we show that the same model architecture can be trained to perform a speech separation task.

关键词： speech normalization voice conversion atypical speech speech synthesis sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Exaggerated Portrait Caricatures Generation Based On Seq2Seq 9

Exaggerated Portrait Caricatures Generation Based On Seq2Seq

引用

9th International Conference on Information Science and Technology (ICIST)

作者： Xu, Kun Tang, Chenwei Lv, Jiancheng He, Zhenan Sichuan Univ Coll Comp Sci Chengdu Peoples R China

ISBN: (纸本)9781728121062

Exaggerated portrait caricatures can represent peoples explicit facial characteristics. Recently, there have been increasing interests in exaggerated portrait caricatures generation from the real face images. However, existing methods randomly exaggerate facial features and the effects are not diversified. In this paper, we achieve the extraction of facial structure features and explicit geometry features using sequence-to-sequence model. The extracted facial structure features can be well applied to caricatures generation. In order to avoid destroying the recognition of the characters from exaggerating the input face, we also incorporate the matching threshold loss as a penalty term to constrain the exaggerated expression of facial features. Experiment results on the collected dataset indicate the proposed method can finally get satisfied result.

关键词： Exaggerated portrait caricatures sequence-to-sequence model structure features

来源：评论

学校读者我要写书评

暂无评论

sequence-to-sequence Imputation of Missing Sensor Data 32nd

Sequence-to-Sequence Imputation of Missing Sensor Data

引用

32nd Australasian Joint Conference on Artificial Intelligence

作者： Dabrowski, Joel Janek Rahman, Ashfaqur CSIRO Data61 Brisbane Qld Australia CSIRO Data61 Hobart Tas Australia

ISBN: (纸本)9783030352882;9783030352875

Although the sequence-to-sequence (encoder-decoder) model is considered the state-of-the-art in deep learning sequence models, there is little research into using this model for recovering missing sensor data. The key challenge is that the missing sensor data problem typically comprises three sequences (a sequence of observed samples, followed by a sequence of missing samples, followed by another sequence of observed samples) whereas, the sequence-to-sequence model only considers two sequences (an input sequence and an output sequence). We address this problem by formulating a sequence-to-sequence in a novel way. A forward RNN encodes the data observed before the missing sequence and a backward RNN encodes the data observed after the missing sequence. A decoder decodes the two encoders in a novel way to predict the missing data. We demonstrate that this model produces the lowest errors in 12% more cases than the current state-of-the-art.

关键词： Imputation Interpolation LSTM Encoder-decoder model sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Robust sequence-to-sequence Acoustic modeling with Stepwise Monotonic Attention for Neural TTS 20

Robust Sequence-to-Sequence Acoustic Modeling with Stepwise ...

引用

Interspeech Conference

作者： He, Mutian Deng, Yan He, Lei Beihang Univ Sch Comp Sci & Engn Beijing Peoples R China Microsoft Beijing Peoples R China

Neural TTS has demonstrated strong capabilities to generate human-like speech with high quality and naturalness, while its generalization to out-of-domain texts is still a challenging task, with regard to the design of attention-based sequence-to-sequence acoustic modeling. Various errors occur in those inputs with unseen context, including attention collapse, skipping, repeating, etc., which limits the broader applications. In this paper, we propose a novel stepwise monotonic attention method in sequence-to-sequence acoustic modeling to improve the robustness on out-of-domain inputs. The method utilizes the strict monotonic property in TTS with constraints on monotonic hard attention that the alignments between inputs and outputs sequence must be not only monotonic but allowing no skipping on inputs. Soft attention could be used to evade mismatch between training and inference. The experimental results show that the proposed method could achieve significant improvements in robustness on out-of-domain scenarios for phoneme-based models, without any regression on the in-domain naturalness test.

关键词： sequence-to-sequence model attention speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Neural Machine Translation for Multilingual Grapheme-to-Phoneme Conversion 20

Neural Machine Translation for Multilingual Grapheme-to-Phon...

引用

Interspeech Conference

作者： Sokolov, Alex Rohlin, Tracy Rastrow, Ariya Amazoncom Inc Seattle WA 98170 USA

Grapheme-to-phoneme (G2P) models are a key component in Automatic Speech Recognition (ASR) systems, such as the ASR system in Alexa, as they are used to generate pronunciations for out-of-vocabulary words that do not exist in the pronunciation lexicons (mappings like”e c h o” → ”E k oU”). Most G2P systems are monolingual and based on traditional joint-sequence based n-gram models [1, 2]. As an alternative, we present a single end-to-end trained neural G2P model that shares same encoder and decoder across multiple languages. This allows the model to utilize a combination of universal symbol inventories of Latin-like alphabets and cross-linguistically shared feature representations. Such model is especially useful in the scenarios of low resource languages and code switching/foreign words, where the pronunciations in one language need to be adapted to other locales or accents. We further experiment with word language distribution vector as an additional training target in order to improve system performance by helping the model decouple pronunciations across a variety of languages in the parameter space. We show 7.2% average improvement in phoneme error rate over low resource languages and no degradation over high resource ones compared to monolingual baselines. Copyright © 2019 ISCA

关键词： grapheme-to-phoneme conversion sequence-to-sequence model multilingual machine translation pronunciation generation

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：