A Benchmark System for Indian Language Text Recognition

2020 ◽  
pp. 74-88
Author(s):  
Krishna Tulsyan ◽  
Nimisha Srivastava ◽  
Ajoy Mondal ◽  
C. V. Jawahar
Keyword(s):  
Text Recognition ◽  
Indian Language ◽  
Benchmark System ◽  
Language Text

scholarly journals A Context-based Numeral Reading Technique for Text to Speech Systems

2018 ◽  
Vol 8 (6) ◽  
pp. 4533
Author(s):  
Soumya Priyadarsini Panda ◽  
Ajit Kumar Nayak
Keyword(s):  
Execution Time ◽  
Indian Languages ◽  
Text To Speech ◽  
Indian Language ◽  
Novel Technique ◽  
Input Text ◽  
Reading Technique ◽  
Intelligible Speech ◽  
Language Text

This paper presents a novel technique for context based numeral reading in Indian language text to speech systems. The model uses a set of rules to determine the context of the numeral pronunciation and is being integrated with the waveform concatenation technique to produce speech out of the input text in Indian languages. For this purpose, the three Indian languages Odia, Hindi and Bengali are considered. To analyze the performance of the proposed technique, a set of experiments are performed considering different context of numeral pronunciations and the results are compared with existing syllable-based technique. The results obtained from different experiments shows the effectiveness of the proposed technique in producing intelligible speech out of the entered text utterances compared to the existing technique even with very less storage and execution time.

A Unified Parser for Developing Indian Language Text to Speech Synthesizers

2016 ◽  
pp. 514-521 ◽  
Author(s):  
Arun Baby ◽  
Nishanthi N.L. ◽  
Anju Leela Thomas ◽  
Hema A. Murthy
Keyword(s):  
Text To Speech ◽  
Indian Language ◽  
Language Text

scholarly journals Machine Learning Techniques for Sentiment Analysis of Indian Languages

2019 ◽  
Vol 8 (2S11) ◽  
pp. 3630-3636
Keyword(s):  
Machine Learning ◽  
Natural Language Processing ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Machine Learning Techniques ◽  
Indian Languages ◽  
Indian Language ◽  
Learning Techniques ◽  
Textual Data ◽  
Language Text

Sentiment Analysis is the domain of automatically understanding the emotions, feelings, opinions in a textual data. It is a way of understating how a product, brand, service, idea or an event is viewed by common people, customers and stakeholders. Sentiment Analysis Systems are used by politicians, business leaders, developers and researchers to infer useful information as per their specific needs. It is used in business decision making process to value the views of the customers. Sentiment analysis has become a hot topic of scientific and market research in the field of natural Language Processing. India is a large populated country and the number of Internet users is also huge. Most people share their experience in English. However, during the last decade, due to the accessibility of Internet and evolution in language modelling people express their views in their own native Indian language. With the increase in Indian language text, researchers find it quite fascinating to infer valuable information from this unstructured text data. A number of machine learning techniques have been applied on this textual data set. Basic concepts of Sentiment analysis shall be discussed with focus on Indian language text in this paper. Due to on availability of rich lexicon resources for unsupervised learning techniques and better evaluation measures for the Supervised learning techniques, the later become the first choice for researchers in the field of Natural Language Processing. A comparative analysis shall be made for various supervised machine learning techniques in the context of Indian languages.

scholarly journals Sindhi Handwritten Text Recognition Using SVM

2021 ◽  
Vol 10 (3) ◽  
pp. 1627-1631
Keyword(s):  
Feature Extraction ◽  
Complex Problem ◽  
Training Data ◽  
Text Recognition ◽  
Support Vector ◽  
Text Data ◽  
Handwritten Text ◽  
Handwritten Text Recognition ◽  
Text Feature ◽  
Language Text

In Sindhi Language, handwritten text feature extraction is such a challenging task for all scholars, because different people write in different styles or manners, to analyze each text is such a complex problem. Feature extraction of text segmentation, classifying each character and labelling for training data to recognize text for different handwritings and testing for analyzing features of providing handwritten text data .In this research, SVM (support vector machine) is used for analyzing and tokenizing each character or word of Sindhi Language text and transform into suitable information with efficiency & accuracy. The research is not only useful for improving the knowledge of Sindhi Handwritten Text Recognition but it can be beneficial for other recognition systems

Sign in / Sign up

Export Citation Format

Share Document