اختيار الموقع            تسجيل دخول
 

هندسة اللغة:
بيانات الدورية
أعداد قيد الطبع
  هندسة اللغة:
  
 

[9001100.] رقم البحث : 9001100 -
Automatic Speech Segmentation Using Hybrid Wavelet Features and HMM /
تخصص البحث : Speech Processing, Recognition and Synthesis
  هندسة اللغة: / العدد (2) - مجلد (3) - سبتمبر 2016
  تاريخ تقديم البحث 16/09/2016
  تاريخ قبول البحث 16/09/2016
  عدد صفحات البحث 14 Pages
  Amr M. Gody ( amg00@fayoum.edu.eg - ) - مؤلف رئيسي
  Manal Shaaban ( manal.mohammed66@yahoo.com - )
  Amr Saleh ( aae00@fayoum.edu.eg - )
  Mel scale, BTE, MFCC, HTK, Gaussian Mixture, Speech Segmentation
  In this research, a novel feature set is used to automatically segment speech signal. Automatic segmentation is very useful especially for large database. A hybrid features model is created from wavelet packet analysis and mel-scale is used to train Hidden Markov Model (HMM) for phone boundary detection. HMM is implemented using the Hidden Markov Model Toolkit (HTK).The database (Ked-TIMIT) is used for result verifications and Mel Frequency Cepstral Coefficients (MFCC) is used as reference for evaluating the results of the proposed Hybrid model. The results are categorized for vowels, consonants and short phones. Phone duration and start location are used as metrics to evaluate the system success rate. Success rate of 74% is achieved for consonant detection, 72% for vowel detection and 58% for short phone detection. Using the simple metric that relies only on boundary locations but ignoring duration, the achieved results are 92.5% for consonant detection, 90% for vowel detection and 77.5% for short phoneme detection. In addition to boundary detection the proposed hybrid model is utilized to compare newly developed features called Mel scale Best Tree Encoding (Mel-BTE ) to the mostly used popular features MFCC along with all experiments using the same database. The relative results for Mel-BTE with respect to MFCC are 94.77% for consonant detection, 87.5% for vowel detection and 93.33% for short phoneme detection.
  Download Paper

[9001101.] رقم البحث : 9001101 -
Sentiment Analysis System for Arabic Articles News (SASAAN) /
تخصص البحث : Social Networks Contents Analysis
  هندسة اللغة: / العدد (2) - مجلد (3) - سبتمبر 2016
  تاريخ تقديم البحث 16/09/2016
  تاريخ قبول البحث 16/09/2016
  عدد صفحات البحث 11 Pages
  Fawzia Zaki Farahat ( Eng.fawzia@gmail.com - ) - مؤلف رئيسي
  Alaa Hamouda ( Alaa_hamouda@azhar.edu.eg - )
  Ali Mahmoud Rashed ( rashed@etcp.edu.eg - )
  Opinion Sentences, Arabic Grammar, Target Sentences, Opinion Lexicon, Machine Learning (SVM).
  Sentiment analysis (also known as opinion mining) identifies and analyzes opinions and emotions in many domains (e.g. news, articles, product reviews, blogs, forum posts). Opinion mining is very important for companies, governments and every one interested to know opinion about special subject. This research discusses the problem of identifying opinion in Arabic news and Arabic articles. Most previous researches focused on extracting opinion from direct sentiments at the level of the article. Considering that an article contains large number of sentences, and some of these sentences may be about different topics and may be not opinion sentence, we propose a new methodology for sentiment analysis for Arabic articles. It starts with identifying opinion sentence related to the target of the article. Machine learning and Typed Dependency Relations (TDR) are used to identify the opinion sentences. Sentences that contain one word of high frequency nouns or adjectives are classified as target sentences. Then opinion lexicon is built using machine learning based on dataset that was collected from different domains (e.g. politics, economy, government, sports, and art). Three methods are used to identify opinion mining in articles. A method that depends on Opinion Lexicon achieved F-score of 62.8%. Machine learning (SVM) method achieved F-score 42.63%. whereas, our method that identifies opinion sentences that are related to the target of article then using opinion lexicon achieved the best results (F-score of 73.25%). So we recommended to identify opinion sentences that are related to the target of the article, then use the opinion lexicon to know the opinion.
  Download Paper

[9001102.] رقم البحث : 9001102 -
Handling Instability using Semantic Case Based Reasoning /
تخصص البحث : Semantic Web and Ontology Languages
  هندسة اللغة: / العدد (2) - مجلد (3) - سبتمبر 2016
  تاريخ تقديم البحث 16/09/2016
  تاريخ قبول البحث 16/09/2016
  عدد صفحات البحث 16 Pages
  Passent ElKafrawy ( basant.elkafrawi@science.menofia.edu.eg - ) - مؤلف رئيسي
  Rania A. Mohamed ( rania.a.mohamed@gmail.com - )
  Uncertainty information, Case-Based Reasoning, Ontology, Semantic Knowledge.
  This paper proposes a joint effort technique between Case-Based Reasoning (CBR) and Semantic learning (SCBR) to handle instability in the cases recovery process with a specific end goal to cover more significant things in consequence of pursuit procedure. The coordinated effort strategy utilizes Ontological learning and Case-Based Reasoning in positioning (CBR) improvement. We diagram how Semantic Case-based Reasoning methodology can be actualized to handle the instability data keeping in mind the end goal to recognize trusted and untrusted members. The methodology could be stretched out to other application spaces of CBR. The real preferred standpoint of such approach is that Semantic information frameworks are intended to comprehend the substance of this present reality as precisely as would be prudent inside the information set. This paper additionally acquaints another methodology with Case-Based Reasoning (CBR) utilizing Semantic learning (SCBR) where it can deal with a few issues in customary CBR.
  Download Paper

 


Powered by Future Library Software.All rights reserved © CITC - Mansoura University. Sponsored by Mansoura University Privacy Policy