2014 International Conference on Asian Language Processing (IALP)最新文献_第3页

Nonlinear analysis of natural vs. HTS-based synthetic speech 自然语音与基于hts的合成语音的非线性分析

2014 International Conference on Asian Language Processing (IALP) Pub Date : 2014-12-04 DOI: 10.1109/IALP.2014.6973518

H. Patil, S. Adarsa

引用次数: 0

Effectiveness of multiscale fractal dimension-based phonetic segmentation in speech synthesis for low resource language 基于多尺度分形维数的语音分割在低资源语言语音合成中的有效性

2014 International Conference on Asian Language Processing (IALP) Pub Date : 2014-12-04 DOI: 10.1109/IALP.2014.6973508

Mohammadi Zaki, Nirmesh J. Shah, H. Patil

{"title":"Effectiveness of multiscale fractal dimension-based phonetic segmentation in speech synthesis for low resource language","authors":"Mohammadi Zaki, Nirmesh J. Shah, H. Patil","doi":"10.1109/IALP.2014.6973508","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973508","url":null,"abstract":"Phonetic segmentation plays a key role in developing various speech applications. In this work, we propose to use various features for automatic phonetic segmentation task for forced Viterbi alignment and compare their effectiveness. We propose to use novel multiscale fractal dimension-based features concatenated with Mel-Frequency Cepstral Coefficients (MFCC). The novel features are expected to capture additional nonlinearities in speech production which should improve the performance of segmentation task. However, to evaluate effectiveness of these segmentation algorithms, we require manual accurate phoneme-level labeled data which is not available for low resource languages such as Gujarati (a low resource language and one of the official languages of India). In order to measure effectiveness of various segmentation algorithms, HMM-based speech synthesis system (HTS) for Gujarati have been built. From the subjective and objective evaluations, it is observed that FD-based features for segmentation work moderately better than other state-of-the-art features such as MFCC, Perceptual Linear Prediction Cepstral Coefficients (PLP-CC), Cochlear Filter Cepstral Coefficients (CFCC), and RelAtive SpecTrAl (RASTA)-based PLP-CC. The Mean Opinion Score (MOS) and the Degraded-MOS, which are the measures of naturalness indicate an improvement of 9.69% with the proposed features from the MFCC (which is found to be the best among the other features) based features.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116110483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

The analysis on mistaken segmentation of Tibetan words based on statistical method 基于统计方法的藏文词分词错误分析

2014 International Conference on Asian Language Processing (IALP) Pub Date : 2014-12-04 DOI: 10.1109/IALP.2014.6973513

Congjun Long, Yiyong Lan, Xiaobing Zhao

引用次数: 1

The usage of Zongshi 宗师的用法

2014 International Conference on Asian Language Processing (IALP) Pub Date : 2014-12-04 DOI: 10.1109/IALP.2014.6973470

Shuqin Shi, Kaihong Yang

引用次数: 0

Hybrid approach for aligning parallel sentences for languages without a written form using standard Malay and Malay dialects 使用标准马来语和马来方言对没有书面形式的语言平行句进行对齐的混合方法

2014 International Conference on Asian Language Processing (IALP) Pub Date : 2014-12-04 DOI: 10.1109/IALP.2014.6973524

Y. Khaw, T. Tan

引用次数: 2

Semantic conceptual primitives computing in text classification 文本分类中的语义概念原语计算

2014 International Conference on Asian Language Processing (IALP) Pub Date : 2014-12-04 DOI: 10.1109/IALP.2014.6973472

Quan Zhang, Yi Yuan, Xiangfeng Wei, Zhejie Chi, Peimin Cong, Yihua Du

引用次数: 1

Concepts identification of an NL query in NLIDB systems NLIDB系统中NL查询的概念识别

2014 International Conference on Asian Language Processing (IALP) Pub Date : 2014-12-04 DOI: 10.1109/IALP.2014.6973483

Saikrishna Srirampur, Ravi Chandibhamar, Ashish Palakurthi, R. Mamidi

引用次数: 7

An extracted database content from WordNet for Natural Language Processing and Word Games 从WordNet中提取的用于自然语言处理和文字游戏的数据库内容

2014 International Conference on Asian Language Processing (IALP) Pub Date : 2014-12-04 DOI: 10.1109/IALP.2014.6973502

Josephine E. Petralba

{"title":"An extracted database content from WordNet for Natural Language Processing and Word Games","authors":"Josephine E. Petralba","doi":"10.1109/IALP.2014.6973502","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973502","url":null,"abstract":"WordNet which is available online and in desktop applications, is an English dictionary where the synonym sets of group of words are linked by means of semantic relations such as hyponymy, meronymy and entailment, among others. The main objective of this paper is to provide the Natural Language Processing (NLP) researchers and Word Game developers with a database such that WordNet content are accessed using simple Structured Query Language (SQL) queries. A distribution copy of Wordnet 3.0 database was downloaded, and loaded into a mySQL database. It was then migrated to Oracle where the database processing to accomplish the objectives of this project was performed. There were 7 tables, 32 materialized views and 4 stored functions constructed. It is at the WordNet dictionary displays that an NLP researcher will initially investigate what Wordnet content he/she needs. Most of the objects were created with reference to the displays. The aim was to come-up with simple SQLs such that the output of an SQL is similar to what is displayed online. Queries to extract content for some Word Games such as HangarooTM and Batang Henyo™ (Genius Child) exemplified the use of this project for Word Games. For Oracle users, distribution copies were made available in a collection of SQL scripts. Non-Oracle users were provided with Excel spreadsheets, Comma Separated Values (CSV) and eXtended Markup Language (XML) files that they can import or load.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126660200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Classification of phonemes using modulation spectrogram based features for Gujarati language 基于调制谱图特征的古吉拉特语音素分类

2014 International Conference on Asian Language Processing (IALP) Pub Date : 2014-12-04 DOI: 10.1109/IALP.2014.6973506

Anshu Chittora, H. Patil

{"title":"Classification of phonemes using modulation spectrogram based features for Gujarati language","authors":"Anshu Chittora, H. Patil","doi":"10.1109/IALP.2014.6973506","DOIUrl":"https://doi.org/10.1109/IALP.2014.6973506","url":null,"abstract":"In this paper, features extracted from modulation spectrogram are used to classify the phonemes in Gujarati language. Modulation spectrogram which is a 2-dimensional (i.e., 2-D) feature vector, is then reduced to a smaller feature dimension by using the proposed feature extraction method. Gujarati database was manually segmented in 31 phoneme classes. These phonemes are then classified using support vector machine (SVM) classifier. Classification accuracy of phoneme classification is 94.5 % as opposed to classification with the state-of-the-art feature set Mel frequency cepstral coefficients (MFCC), which yields 92.74 % classification accuracy. Classification accuracy for broad phoneme classes, viz., vowel, stops, nasals, semivowels, affricates and fricatives is also determined. Phoneme classification in their respective classes is 95.03 % correct with the proposed feature set. Fusion of MFCC with the proposed feature set is performing even better, giving phoneme classification accuracy of 95.7%. With the fusion of features phoneme classification in sonorant and obstruent classes is found to be 97.01 % accurate.","PeriodicalId":117334,"journal":{"name":"2014 International Conference on Asian Language Processing (IALP)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132623842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

A rule-based method for Chinese punctuations processing in sentences segmentation 基于规则的汉语分句标点处理方法

2014 International Conference on Asian Language Processing (IALP) Pub Date : 2014-12-04 DOI: 10.1109/IALP.2014.6973504

Jing Wang, Yun Zhu, Yaohong Jin

引用次数: 1