检索结果-内蒙古大学图书馆

text normalization using memory augmented neural networks

SPEECH COMMUNICATION 2019年 109卷 15-23页

作者： Pramanik, Subhojeet Hussain, Aman VIT Univ Vandaloor Kelambakkam Rd Chennai Tamil Nadu India

We perform text normalization, i.e. the transformation of words from the written to the spoken form, using a memory augmented neural network. With the addition of dynamic memory access and storage mechanism, we present a neural architecture that will serve as a language-agnostic text normalization system while avoiding the kind of unacceptable errors made by the LSTM-based recurrent neural networks. By successfully reducing the frequency of such mistakes, we show that this novel architecture is indeed a better alternative. Our proposed system requires significantly lesser amounts of data, training time and compute resources. Additionally, we perform data up-sampling, circumventing the data sparsity problem in some semiotic classes, to show that sufficient examples in any particular class can improve the performance of our text normalization system. Although a few occurrences of these errors still remain in certain semiotic classes, we demonstrate that memory augmented networks with meta-learning capabilities can open many doors to a superior text normalization system.

关键词： text normalization Differentiable Neural Computer Deep learning

来源：评论

学校读者我要写书评

暂无评论

text normalization Infrastructure that Scales to Hundreds of Language Varieties 11

Text Normalization Infrastructure that Scales to Hundreds of...

引用

11th International Conference on Language Resources and Evaluation (LREC)

作者： Chua, Mason van Esch, Daan Coccaro, Noah Cho, Eunjoon Bhandari, Sujeet Jia, Libin Google LLC 1600 Amphitheatre Pkwy Mountain View CA 94043 USA

ISBN: (纸本)9791095546009

We describe the automated multi-language text normalization infrastructure that prepares textual data to train language models used in Google's keyboards and speech recognition systems, across hundreds of language varieties. Training corpora are sourced from various types of data sets, and the text is then normalized using a sequence of hand-written grammars and learned models. These systems need to scale to hundreds or thousands of language varieties in order to meet product needs. Frequent data refreshes, privacy considerations and simultaneous updates across such a high number of languages make manual inspection of the normalized training data infeasible, while there is ample opportunity for data normalization issues. By tracking metrics about the data and how it was processed, we are able to catch internal data preparation issues and external data corruption issues that can be hard to notice using standard extrinsic evaluation methods. Showing the importance of paying attention to data normalization behavior in large-scale pipelines, these metrics have highlighted issues in Google's real-world speech recognition system that have caused significant, but latent, quality degradation.

关键词： language model text normalization internationalization industrial systems data mining data processing scale less-resourced languages

来源：评论

学校读者我要写书评

暂无评论

text normalization for Indonesian text-to-Speech (TTS) using Rule-Based Approach: A Dataset and Preliminary Study 4

Text Normalization for Indonesian Text-to-Speech (TTS) using...

引用

4th IEEE International Conference on Computer and Informatics Engineering (IC2IE)

作者： Maghfur, Nana Mulyana Ibrohim, Muhammad Okky Fahmi, Junaedi Putera, Achmad Satria Riandi, Oskar Univ Singaperbangsa Fac Comp Sci Karawangan Indonesia Univ Indonesia Fac Comp Sci Depok Indonesia PT Bahasa Kinerja Utama Kota Jakarta Timur Indonesia

ISBN: (纸本)9781665442886

text-to-Speech (TTS) is a technology that is currently widely used for several purposes both for academic/ non-commercial and industry/commercial purposes. In several cases, some researchers on the TTS field adding a text normalization process for normalizing text that will be used for TTS input to enhance the TTS performance itself. In this paper, we present a rule-based approach to make an Indonesian text normalization dataset that has a raw text and a spoken form of it for enhancing Indonesian text-to-Speech (TTS) performance. We conduct a set of rule-based for normalizing Indonesian text as an input for the TTS system. Using those rule-based, we generated a dataset and correct it manually so that we have a gold standard for text normalization for Indonesian TTS input. Our approach shows a rule-based can give a good performance for normalizing text for Indonesian TTS with 0.0805 of Word Error Rate (WER).

关键词： text normalization rule-based Indonesian language

来源：评论

学校读者我要写书评

暂无评论

text normalization in Code-Mixed Social Media text 2

Text Normalization in Code-Mixed Social Media Text

引用

IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS)

作者： Dutta, Sukanya Saha, Tista Banerjee, Somnath Naskar, Sudip Kumar Jadavpur Univ Dept Comp Sci & Engn Kolkata India

ISBN: (纸本)9781479983490

This paper addresses the problem of text normalization, an often overlooked problem in natural language processing, in code-mixed social media text. The objective of the work presented here is to correct English spelling errors in co-demixed social media text that contains English words as well as Romanized transliteration of words from another language, in this case Bangla. The targeted research problem also entails solving another problem, that of word-level language identification in code-mixed social media text. We employ a CRF based machine learning approach followed by post-processing heuristics for the word-level language identification task. For spelling correction, we used the noisy channel model of spelling correction. In addition, the spell checker model presented here tackles wordplay, contracted words and phonetic variations. Overall, the word-level language identification achieved 90.5% accuracy and the spell checker achieved 69.43% accuracy on the detected English words.

关键词： text normalization language identification spell checking code-mixed text

来源：评论

学校读者我要写书评

暂无评论

text normalization on Thai Twitter Messages using IPA Similarity Algorithm

Text Normalization on Thai Twitter Messages using IPA Simila...

引用

International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)

作者： Poolsukkho, Sanphet Kongkachandra, Rachada Thammasat Univ Fac Sci & Technol Dept Comp Sci Pathumthanee Thailand

ISBN: (纸本)9781728101644

Twitter often contains many noisy short messages. The noisy text are caused by insertion, transformation, transliteration and onomatopoeia. text normalization is used for solving these noisy text. In this paper, we present the algorithm that can normalize insertion and homophonic transformation words by converting to International Phonetic Alphabet(IPA) and find the most similarity IPA of out-of-vocabulary and IPA of invocabulary using Levenshtein Distance. We used Twitter corpus that contained 2,000 twitter messages for evaluating the proposed algorithm. The experiment result illustrated that the proposed algorithm returned an accuracy of 79.03% when compared to dictionary-based normalization of LextoPlus returned an accuracy 24.19%.

关键词： text normalization International Phonetic Alphabet Twitter Levenshtein Distance

来源：评论

学校读者我要写书评

暂无评论

text normalization for named entity recognition in Vietnamese tweets

引用

Computational Social Networks 2016年第1期3卷 10页

作者： Nguyen, Vu H. Nguyen, Hien T. Snasel, Vaclav Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Electrical Engineering and Computer Science VSB-Technical University of Ostrava Ostrava Czech Republic

Background: Named entity recognition (NER) is a task of detecting named entities in documents and categorizing them to predefined classes, such as person, location, and organization. This paper focuses on tweets posted on Twitter. Since tweets are noisy, irregular, brief, and include acronyms and spelling errors, NER in those tweets is a challenging task. Many approaches have been proposed to deal with this problem in tweets written in English, Germany, Chinese, etc., but none for Vietnamese tweets. Methods: We propose a method that normalizes a tweet before taking as an input of a learning model for NER in Vietnamese tweets. The normalization step detects spelling errors in a tweet and corrects them using an improved Dice's coefficient or n-grams. A Support Vector Machine learning algorithm is employed to learn a classifier using six different types of features. Results and Conclusion: We train our method on a training set consisting of more than 40,000 named entities and evaluate it on a testing set consisting of 3,186 named entities. The experimental results showed that our system achieves state-of-the-art performance with F1 score of 82.13%. © 2016, The Author(s).

关键词： Named entity recognition Spelling error detection and correction text normalization

来源：评论

学校读者我要写书评

暂无评论

text normalization in mandarin text-to-Speech system

Text normalization in mandarin Text-to-Speech system

引用

33rd IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Jia, Yuxiang Huang, Dezhi Liu, Wu Dong, Yuan Yu, Shiwen Wang, Haila Peking Univ Inst Computat Linguist Beijing 100871 Peoples R China France Telecom R&D Beijing Speech & Nat Language Proc Unit Beijing Peoples R China Beijing Univ Posts & Telecommun Beijing Peoples R China

ISBN: (纸本)9781424414833

text normalization is an important component in text-to-Speech system and the difficulty in text normalization is to disambiguate the Non-Standard Words (NSWs). This paper develops a taxonomy of NSWs on the basis of a large scale Chinese corpus, and proposes a two-stage NSWs disambiguation strategy, Finite State Automata (FSA) for initial classification and Maximum Entropy (ME) classifiers for subclass disambiguation. Based on the above NSWs taxonomy, the two-stage approach achieves an F-score of 98.53% in open test, 5.23% higher than that of FSA based approach. Experiments show that the NSWs taxonomy ensures FSA a high baseline performance and ME classifiers make considerable improvement, and the two-stage approach adapts well to new domains.

关键词： text-to-Speech (TTS) text normalization finite state automata maximum entropy classifier

来源：评论

学校读者我要写书评

暂无评论

text normalization with varied data sources for conversational speech language modeling

Text normalization with varied data sources for conversation...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Schwarm, S Ostendorf, M Univ Washington Dept Comp Sci Seattle WA 98195 USA

ISBN: (纸本)0780374029

Collecting sufficient language model training data for good speech recognition performance in a new domain is often difficult. However, there may be other sources of data that are matched in terms of topic or style, if not both. This paper looks at the use of text normalization tools to make these data more suitable for language model training, in conjunction with mixture models to combine data from different sources. We specifically address the task of recognizing meeting speech, showing a small reduction in word error rate over a baseline language model trained from conversational speech data.

关键词： speech recognition error statistics vocabulary text analysis text normalization varied data sources conversational speech language modeling language model training data speech recognition performance mixture models meeting speech word error rate

来源：评论

学校读者我要写书评

暂无评论

text normalization based on Statistical Machine Translation and Internet User Support

Text Normalization based on Statistical Machine Translation ...

引用

11th Annual Conference of the International-Speech-Communication-Association 2010

作者： Schlippe, Tim Zhu, Chenfei Gebhardt, Jan Schultz, Tanja KIT Cognit Syst Lab Karlsruhe Germany

ISBN: (纸本)9781617821233

In this paper, we describe and compare systems for text normalization based on statistical machine translation (SMT) methods which are constructed with the support of internet users. Internet users normalize text displayed in a web interface, thereby providing a parallel corpus of normalized and non-normalized text. With this corpus, SMT models are generated to translate non-normalized into normalized text. To build traditional language-specific text normalization systems, knowledge of linguistics as well as established computer skills to implement text normalization rules are required. Our systems are built without profound computer knowledge due to the simple self-explanatory user interface and the automatic generation of the SMT models. Additionally, no inhouse knowledge of the language to normalize is required due to the multilingual expertise of the internet community. All techniques are applied on French texts, crawled with our Rapid Language Adaptation Toolkit [1] and compared through Levenshtein edit distance [2], BLEU score [3], and perplexity.

关键词： text normalization statistical machine translation rapid language adaptation automatic speech recognition crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Neural text normalization in Speech-to-text Systems with Rich Features

引用

APPLIED ARTIFICIAL INTELLIGENCE 2021年第3期35卷 193-205页

作者： Tran Oanh Thi Bui Viet The Vietnam Natl Univ Int Sch Hanoi Vietnam FPT Univ FPT Technol Res Inst Hanoi Vietnam

This paper presents the task of normalizing Vietnamese transcribed texts in Speech-to-text (STT) systems. The main purpose is to develop a text normalizer that automatically converts proper nouns and other context-specific formatting of the transcription such as dates, time, and numbers into their appropriate expressions. To this end, we propose a solution that exploits deep neural networks with rich features followed by manually designed rules to recognize and then convert these text sequences. We also introduce a new corpus of 13 K spoken sentences to facilitate the process of the text normalization. The experimental results on this corpus are quite promising. The proposed method yields 90.67% in the F1 score in recognizing sequences of texts that need converting. We hope that this initial work will inspire other follow-up research on this important but unexplored problem.

关键词： Convolutional neural network Speech recognition Vietnamese Deep learning text normalization

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：