Kannada Language Research Articles

Assessment of role perception and job performance of ASHAs in Vijyapaura district, Karnataka

Introduction: ASHAs play an important role in the rollout of government health programmes such as the Janani Suraksha Yojana (JSY), a conditional cash transfer scheme to incentivise women to give birth in a health facility. The ASHAs work closely with other frontline workers like Auxiliary Nurse Midwives (ANMs) and Anganawadi Workers (AWWs) to conduct community-level activities. ASHAs also act as health activists in the community who will create awareness on health and its determinants, counsel mothers on key healthy behaviours and mobilise the community towards local health planning and increased utilisation and accountability of the existing health services. Objectives: To evaluate the Role perception and Job Performance of ASHAs. Materials and Methods: A cross sectional study was done on 617 ASHAs. A pre-designed, semi- structured schedule was prepared in accordance with the study objectives. The questionnaire was prepared in English and the interview was conducted in Kannada language by explaining them questions one by one. Data collection was done by interview technique. Results: 603 (97.7%) of ASHAs had positive attitude towards mobilising the community for accessing health services such as ANC, 602 (97.5%) for ANC, 599(97.08%) for institutional delivery, 597 (96.7%) for birth preparedness, 601(97.4%) for new born care, 600(97.2%) towards exclusive breast feeding. 405 (65.6%) ASHAs told that they are actively involved in distributing Iron and Folic acid tablets to pregnant women. 597 (96.7%) ASHAs informed that they educate mothers about exclusive breast feeding, while 471(76.3%) told that they encourage mothers to continue breast feeding when the child is suffering from diarrhoea. It was found that job performance of ASHAs was significantly associated with Age, Days of Training and Duration of service of ASHAs. Conclusion: In order to orient the ASHAs on their job profile and responsibility, there is a need to assess the knowledge and skills of Accredited Soc

Kannada akshara knowledge in primary school children: measurement of accuracy and reaction time using a cross-sectional study design.

Background: Reading acquisition varies between languages, as languages differ in terms of phonology and orthography. Orthographic knowledge is demonstrated to be crucial in literacy acquisition in most orthographies. The literature on acquisition of orthographic knowledge has focused more on alphabetic orthographies and less is understood in alphasyllabary Kannada language. The present study aimed to understand the akshara knowledge acquisition by measuring akshara identification accuracy and reaction time in typically developing Kannada medium primary school children. Methods: The study consisted of 315 typically developing children, 45 each from Grade I through Grade VII between the age range of 5 years 6 months to 12 years 6 months. The children were assessed for akshara identification accuracy and reaction time using a representative sample of 67 akshara selected at four different levels of complexity: vowels in primary form, consonant with inherent vowels, consonant with vowel diacritics, and consonant clusters. The mean performance was compared between the groups using one-way ANOVA with post-hoc Bonferroni test. Results: One-way ANOVA revealed significant main effect (p≤0.05) of Grade on akshara identification accuracy and reaction time. The post-hoc Bonferroni test revealed that the mean akshara identification accuracy improved significantly (p≤0.05) from Grade I to Grade V and reached a plateau at Grade VI. The reaction time significantly reduced from Grade I to Grade IV and there was no significant change beyond Grade V. Conclusion: The children learning to read alphasyllabary Kannada gain mastery over the majority of aksharas during the initial years of formal schooling, which develops completely by Grade VI. The automaticity in naming akshara develops gradually and reaches a plateau by Grade IV. The present findings indicate that children acquire automaticity in naming akshara early, while the akshara knowledge continues to develop.

Polarity Identification for Handwritten Text in Multilingual Documents Using Open Source Optical Character Recognition Tools

Sentimental analysis is a prerequisite for many applications. We propose a model which scans handwritten text in English and Kannada languages by a CamScanner and then translated into editable text by using various Open Source Optical Character Recognition tools. The performances of different OCRs are analyzed and tabulated. Sentimental analysis is performed on the statements written in both English and Kannada languages using Wordnet, Algorithmia Rest API and local dictionaries and we have obtained the satisfied results. The same sentimental analysis module is also applied on customer reviews for the mobile product and reviews are taken from Amazon Web Services. The opinion of the customer about the product can be identified correctly.

Rectifying Incorrectly Part of Speech-Tagged Polysemy Words in Kannada Language for Machine Translation

Polysemy words refer to the same word, but have different context, when used in a single sentence, resulting in variant Part of Speech (POS). Occurrence of these Polysemy words, more than once, in a Kannada sentences, leads to ambiguity and is often cumbersome to translate it to English, due to incorrect interpretation of the sentence. The algorithm proposed is, concentrated on a few examples, which can identify the wrong POS-tagged word in a sentence. The POS tagged sentence is obtained as an input through Shallow parser, and then, by owing to the structure of Kannada language, the algorithm identifies the incorrectly tagged word.

Adaptation and Validation of Reflux Symptom Index Into Kannada Language

The present study aimed to translate, validate the Reflux Symptom Index in Kannada language and to compare its outcomes between normal individuals and individuals with laryngopharyngeal reflux. Cross sectional study design MATERIALS AND METHOD: : The English version of Reflux Symptom Index was translated into Kannada language using standard procedures. A total of 162 participants participated in the study, 81 with laryngopharyngeal reflux and 81 controls. Internal consistency, test-retest reliability, and clinical validity were calculated. Results revealed that the Kannada Reflux Symptom Index exhibited an excellent internal consistency (α=0.87). The average intra-class correlation coefficient was 0.90 and 0.92, indicating excellent test-retest reliability. Independent sample t test revealed a statistically significant difference between the total scores of both the groups, thereby exhibiting good clinical validity of RSI-K (t=42.71, df=158, P < 0.001). The Kannada Reflux Symptom Index is a reliable and valid tool for use in patients with laryngopharyngeal reflux. It can be used as a quick tool to assess laryngopharyngeal reflux.

Mediamorphosis of Regional Newspapers: Utilization of the Internet’s Potential by Kannada Media

The advent of the internet has posed threats as well as offered new opportunities for the traditional news media industry. The innumerable potentials of the internet include instant delivery of news, multimedia content and other user-friendly features to media consumers. Since digital news consumption is proliferating in India, it is important to study how Indian regional newspapers have adapted to new media technological advancements. Using Zamith’s (2008. 9th International Symposium on Online Journalism, 1–8) methodological framework, we identify various potentials of the internet that can be utilized by the traditional media offering news online. The study examines the extent to which Indian regional news sites have incorporated these potentials—interactivity, hypertextuality, multimediality, immediacy, memory, personalization, ubiquity, creativity and other latest new media technologies. Roger Fidler’s ‘mediamorphosis theory’ is employed as a theoretical approach to examine how regional language newspapers are responding to technological advancements. The study looks at three news sites of the most circulated Kannada language (a regional language of Karnataka state) newspapers. Our study finds that Indian regional news sites only partially use the internet’s potentials and are unable to explore some of the internet’s features due to their rigid organizational policies and a lack of multiskilled workforce.

A Phonetic Level Analysis of Dysarthria in Kannada Language

Dysarthria is a motor speech disorder and the most common neurodegenerative disease characterized by low volume in precise articulation, poor coordination of respiratory and phonatory subsystems, irregular pauses and so on. The challenging factor in improving the communication with dysarthria is speech intelligibility. The intelligilibility of speech can be determined by measuring the acoustic characteristics and phonetic structures of speech. In our analysis, we have concentrated on bisyllabic words in the Kannada language. The analysis is carried out with respect to basic acoustic parameters and spectrogram to extract fundamental frequency, formant frequency, jitter, shimmer, HNR and Standard Deviation using PRAAT tool. These results are helpful to identify and differentiate the complex natural frequency of the vocal tract functions with respect to normal subjects and dysarthria subjects. This study provides inputs to increase efficacy in the clinical assessments for monitoring and diagnosing the speech disorders for improving communication among human beings.

Characterising User Content on a Multi-Lingual Social Network

Social media has been on the vanguard of political information diffusion in the 21st century. Most studies that look into disinformation, political influence and fake-news focus on mainstream social media platforms. This has inevitably made English an important factor in our current understanding of political activity on social media. As a result, there has only been a limited number of studies into a large portion of the world, including the largest, multilingual and multicultural democracy: India. In this paper we present our characterisation of a multilingual social network in India called ShareChat. We collect an exhaustive dataset across 72 weeks before and during the Indian general elections of 2019, across 14 languages. We investigate the cross lingual dynamics by clustering visually similar images together, and exploring how they move across language barriers. We find that Telugu, Malayalam, Tamil and Kannada languages tend to be dominant in soliciting political images (often referred to as memes), and posts from Hindi have the largest cross-lingual diffusion across ShareChat (as well as images containing text in English). In the case of images containing text that cross language barriers, we see that language translation is used to widen the accessibility. That said, we find cases where the same image is associated with very different text (and therefore meanings). This initial characterisation paves the way for more advanced pipelines to understand the dynamics of fake and political content in a multi-lingual and non-textual setting.

COMPARISON BETWEEN LEADING APIS USED IN TRANSLATION APPS

Translator Apps for Mobile devices is a mobile application to translate from English to Kannada (Language spoken in Karnataka) and vice versa. In addition translations can be done between other languages as well. And hence, APIs become an important part of the application. There are a lot of different APIs which can be used to perform translations. This paper presents a comparison between the most frequently used API by checking their accuracy, ease of use and other attributes to highlight which API is best used for Translation purposes.

Reliability and Validity of the Kannada Version of the Parental Stress Scale

Background: Parental Stress Scale (PSS) is a self report scale of 18 items which represents positive andnegative components of parenthood. Administration of scale doesn’t require any specific training but as it isself report scale it is important that parents should be able to read it by themselves for better understandingof questions. Therefore it is necessary to translate and validate the tool in local language.Objective: Objective of this study was to translate the Parental Stress Scale in Kannada language and checkits reliability in comparison with original English tool.Methods: Translation procedure was followed according to WHO guidelines for translation and adaptationof instruments. The original English version of PSS was translated by two translators into Kannada. It wasfurther subjected to expert panel opinion. Amendments were done in the Kannada version as per the panel’sopinion. A reverse translation of the amended tool was then done by a translator back to English fromKannada. The translated scale was later tested for reliability and validity.Results: The Cronbach’s alpha value of translated version of PSS was found to be 0.915 with an ICC valueof 0.82. The translated version of tool was found to be reliable and culturally acceptable in North-Karnatakaregion.Conclusion: The translated version of PSS has an excellent internal consistency and good reliability. It canbe used to measure parental stress scores among the population from North-Karnataka region.

Speech Classification for Kannada Language

Speech classification is one of the challenging issues in speech processing. In this paper, we have done speech classification for the Kannada language. We have gathered a speech database from children aged 4-6 years. The dataset collected are pre-processed and speech feature extraction is done using Mel Frequency Cepstral Coefficients (MFCC) technique. After feature extraction Kannada alphabets are classified using six different Machine Learning (ML) classifiers. The classifier accuracies are compared with each other. Amongst the Deep Learning classifiers, Recursive Neural Network (RNN) gave the highest accuracy of around 93.6 %( for 300 epochs) and Random Forest (RF) gave the highest accuracy of around 88.9% which is a Machine Learning classifier.

Identification of regional dialects of Telugu language using text independent speech processing models

Telugu language is one of the important languages in the world. The language that is spoken by most of the people in a region is called as dialect. In the recent days, speech recognition system is present in almost all electronic devices. In this, dialects of particular language perform a vital role. The accurate dialects identification technique helps in not only enhancing its features but also expected to provide in modern services in health and telemedicine for older and homebound peoples. Like any other language, even Telugu language has diversified itself into different dialects viz., Telangana, Kostha Andhra, and Rayalaseema. Combination of all the dialects is the language TELUGU and it is a perfect blend of elegance in Sanskrit, sweetness in Tamil along with the essence of Kannada language. The formation of dialects can be of different reasons. For speech processing research, till today there is no standard speech database created for Telugu dialects. In this paper we developed a speech database that can be utilized for the recognition of Telugu dialects and we had applied two modeling techniques that are, Hidden Markov Model (HMM) and Gaussian mixture model (GMM) in order to recognize the dialects of Telugu language by using speech independant utterances. We imposed Mel-Frequency Cepstral Coefficient for extracting the spectral features from the obtained speech data and observed that GMM provides better accurate results than HMM.

Communication Attitude of Kannada-Speaking School-Age Children Who Do and Do Not Stutter

Background: A large body of evidence suggests that the Communication Attitude Test (CAT) is a reliable and valid tool for assessing the speech-associated attitude of school-age children who stutter (CWS). Objective: The purpose of the present study was to adapt and validate the CAT for the Kannada-speaking school-age CWS. Methods: The original version of the CAT was forward- and back-translated by the first author. The Communication Attitude Test Kannada (CAT-K) was then administered to 293 children who do not stutter (CWNS) and 100 CWS. All children were native speakers of the Kannada language and were between the ages of 7 and 14 years. The Stuttering Severity Instrument-fourth edition (SSI-4) was used to estimate the severity of stuttering. Results: The data revealed that, in comparison to CWNS, the CWS’ mean CAT-K score was significantly higher, and a significant effect of stuttering severity and age on mean attitude scores was observed. In addition, results showed that the CAT-K is a reliable and valid test. Conclusion: The findings suggest the presence of a negative attitude in Kannada-speaking CWS and that the CAT-K is a useful tool in the assessment of Kannada school-age CWS. Given the need for speech-language pathologists to address a speech-associated negative attitude in CWS, incorporating the CAT-K as part of the diagnostic assessment of stuttering is valuable.

Corpora Based Classification to Perform Sentiment Analysis in Kannada Language

In this modern era, the users’ opinions play an uncanny role in understanding how well a product has satisfied the customer requirements, so that the producer can change the product to suit the customers’ demands and these reviews also help the new consumers to decide on whether to purchase the product or not. Analysis of a particular entity's feelings in terms of positive, negative or neutral polarization is known as ‘Sentiment Analysis’. SentimentAnalysis is a sub-domain of opinion mining.Here the analysis is focused on the mining of emotions and opinions of the people towards a specific topic. The emotions and opinions are collected in the form of organized, semi-organized or amorphous data. As the world is slowly progressing towards regional languages, this article talks about extracting the opinions of a product in Kannada and performing analysis about these reviews and classifying them accordingly. The dataset or the corpus is scarce as it is not English. The limited corpus is being collected via website – https://gadgetloka.com through an API. However, extracting inclusive opinion manually from huge amorphous data would be a tedious task. An automated system called 'Sentiment Analysis or Opinion Mining' can solve this problem, which can analyze and extract the observation of the user throughout the reviews. In this classifier of review analysis, the process classifies the review via corpus, which is a huge collection of pre-defined data. The API that has been used is Python-Beautiful Soup via utf-8 text recognition method to parse Kannada characters. The reviews are converted to text sentence and each word of the sentence are broken down. Data mining task is done to find the sentiment of each word by comparing it with two stored files named as good.txt and bad.txt. Further, the analyzed result is given through text output as Positive, Negative or Neutral sentiments based on their weights.

Information Gathering Pattern of Writers in Kannada Language at Mysuru, Karnataka: A Study

The information gathering pattern is the technique of searching for the information. The Kannada writers played major role in the development of Kannada literature. The present study tries to find out the ways of access to information by the writers in Kannada Language, frequency of visit to the library, types of libraries visited, environmental issues effecting information needs and information gathering, preferred material used and preferred language materials referred to seek information. For this purpose the researchers prepared a well structured questionnaire as a tool for data collection and same was analyzed and presented with useful percentage analysis and suitable table for presentation of data. The article summarizes the results highlighting the major findings, suggestions and conclusion.

Evaluation of knowledge and practice of ASHAs, regarding child health services in Vijyapaura District, Karnataka.

Background and Aims:NHM has created a cadre of trained female community health activists called Accredited Social Health Activists (ASHAs) to mobilize the community toward increased utilization of existing health services. ASHAs play an important role in the rollout of government health programs such as the Janani Suraksha Yojana (JSY), a conditional cash transfer scheme to incentivize women to give birth in a health facility. The ASHAs work closely with other frontline workers like Auxiliary Nurse Midwives (ANMs) and Anganawadi Workers (AWWs) to conduct community-level activities.Method:A cross-sectional study was conducted in 11 months. A pre-designed, semi- structured questionnaire was prepared in accordance with the study objectives. The questionnaire was prepared in English and the interview was conducted in Kannada language by explaining them questions one by one. Data collection was done by interview technique.Results:Out of 617 ASHAs interviewed, 580 (94%) ASHAs had proper knowledge about exclusive breast feeding and the duration, 560 (90.7%) told colostrum was necessary to the baby. Only 323 (52.3%) ASHAs had correct knowledge regarding schedule of immunization. 580 (94%) ASHAs could tell when the weaning should be started correctly and 611 (99%) ASHAs knew about ORS packets and the steps that went in preparing it.Conclusion:Generally, knowledge of ASHAs about care of new-born and child health care was considerably good. However, knowledge of ASHAs about the immunization schedule was found to be inadequate.

Creation and Instigation of Triphone based Big-Lexicon Speaker-Independent Continuous Speech Recognition Framework for Kannada Language

This paper proposes a framework that is intended to do the comparably accurate recognition of speech and in precise, continuous speech recognition (CSR) based on triphone modelling for Kannada dialect. For designing the proposed framework, the features from the speech data are obtained from the well-known feature extraction technique Mel-frequency cepstral coefficients (MFCC) and from its transformations, like, linear discriminant analysis (LDA) and maximum likelihood linear transforms (MLLT) are obtained from Kannada speech data files. At that point, the system is trained to evaluate the hidden Markov model (HMM) parameters for continuous speech (CS) data. The persistent Kannada speech information is gathered from 2600 speakers (1560 men and 1040women) of the age bunch in the scope of 14 years-80 years. The speech information is acquired from different geographical regions of the Karnataka (one of the 29 states situated in the southern part of India) state under degraded condition. It comprises of 21,551 words that spread 30 locales. The performance evaluation of both monophone and triphone models concerning word error rate (WER) is done and the obtained results are compared with the standard databases such as TIMIT and aurora4. A significant reduction in WER is obtained for triphone models. The speech recognition (SR) rate is verified for both offline and online recognition mode for all the speakers. The results reveal that the recognition rate (RR) for Kannada speech corpus has got a better improvement over the state-of-the-art existing databases.

Mispronunciation Detection for Spoken Isolated Words using Segmentation and Classification under Low Resource Conditions for Kannada Language

Relocation makes it inevitable for a person to learn the local pronunciations correctly. With the advent of mobile phones, language learning can be made easy and flexible. Our research involves Kannada Kali, a mobile and cloud based application that is being developed to assist people in learning the correct pronunciations of Kannada (a language spoken in India). Automatic Speech Recognition systems which are used to aid pronunciation training require to be trained on sufficient amount of spoken target language data. Since collecting such data in not easy, the objective of our research is to detect mispronounced segments of words with minimal data. When there is scarcity of data, a comparative approach where spoken word segments are compared with the canonical pronunciations is more effective for detecting anomaly in pronunciation. Since syllables are basic independent units of pronunciation, the spoken words are segmented into syllables for effective comparison and feedback. We propose an unsupervised segmentation method called Spectrogram Formant Contour Analysis that detects syllable boundaries by analysing the change in contours of the formants in the spoken word spectrograms. The task of mispronunciation detection is more effective when the application can identify the actual syllable pronounced and communicate the correct pronunciation to the user. For the purpose of syllable classification, our method employs a novel approach where a model is trained on phonemes and given syllables as input for identification. Our study includes comparing the performance of three machine learning algorithms, namely, Convolution Neural Network, Support Vector Machines and K-Nearest Neighbours on the task of identifying phonemes when they are trained on minimal data. The accuracy of KNN on phoneme classification was the best with 80% for clean and 60% for noisy data. In case of our initial results on syllable classification for Kannada Kali, Support Vector Machines gave the highest accuracy of almost 30%.

Television Viewing Preferences of Kannada Speaking Population of Bangalore – A Special Emphasis on Kannada Sports Channel

As a nation India has more than 1600 dialects, 30 plus languages spoken by more than one million people; there are around 32 million users of kannada language in the country (KPMG, 2017). Among the various entertainment that the masses enjoy, majority of the population enjoy playing and watching sports, it is believed that people enjoy watching sports or entertainment in the language that they are most comfortable to speak. Bangalore being the capital of Karnataka is an IT hub and has a wide floating population; the capital is trying to keep the state language alive. A well-known television network is planning to start a kannada sports channel. It is interested in knowing the feasibility of introducing an exclusive sports channel in kannada. The researchers have conducted this study to help the channel to understand the TV viewing habit &amp; preferences, related to sports, of the Kannada speaking population of Bangalore. The researchers also aim to find out how likely, the target group is to watch their favorite sports in Kannada. Based on the results of the analysis of data collected, it can be seen that as a large percentage of respondents have interest in watching Sports in Kannada and have been watching and enjoying the IPL broadcasted in Kannada on Suvarna Plus in 2018, therefore investing in launching a Kannada Star Sports channel appears fruitful. Keeping the target audiences’ content viewing preferences in mind, major TV channels can aim at broadcasting sports such as Cricket, Football &amp; Kabaddi in Kannada.

Automatic dialect identification system for Kannada language using single and ensemble SVM algorithms

In this paper, an automatic dialect identification (ADI) system is proposed by extracting spectral and prosodic features for Kannada language. A new dialect dataset is collected from native speakers of Kannada language (A Dravidian language). This dataset includes five distinct dialects of Kannada language representing five geographical regions of Karnataka state. Investigation of the significance of spectral and prosodic variations on five Kannada dialects is carried out. Mel-frequency cepstral coefficients (MFCCs), spectral flux, and entropy are used as representatives of spectral features. Besides, pitch and energy features are extracted as representatives of prosodic parameters for identification of dialects. These raw feature vectors are further processed to get a new derived feature vectors by using statistical processing. In this paper, a single classifier based multi-class support vector machine (SVM) and multiple classifier based ensemble SVM (ESVM) techniques are employed for classification of dialects. The effectiveness and performance evaluation of the explored features are carried out on newly collected Kannada speech corpus, with five Kannada dialects and internationally known standard Intonation Variation in English (IViE) dataset with nine British English dialects. Experimental results have demonstrated that the derived feature vectors performs better when compared to raw feature vectors. However, ESVM technique has demonstrated better performance over a single SVM. Spectral and prosodic features have resulted individually with the dialect recognition performance of 83.12% and 44.52% respectively. Further, the complementary nature of both spectral and prosodic features is evaluated by combining both feature vectors for dialect recognition. However, an increase in dialect recognition performance of about 86.25% is observed. This indicates the existence of complementary dialect specific evidence with spectral and prosodic features. The experiments conducted on standard IViE corpus have shown a higher recognition rate of 91.38% using ESVM. Proposed ADI systems with derived features have shown better performance over the state-of-the-art i-vector feature based systems on both datasets.