Hindi Sentences Research Articles

Surprisal From Language Models Can Predict ERPs in Processing Predicate-Argument Structures Only if Enriched by an Agent Preference Principle.

Language models based on artificial neural networks increasingly capture key aspects of how humans process sentences. Most notably, model-based surprisals predict event-related potentials such as N400 amplitudes during parsing. Assuming that these models represent realistic estimates of human linguistic experience, their success in modeling language processing raises the possibility that the human processing system relies on no other principles than the general architecture of language models and on sufficient linguistic input. Here, we test this hypothesis on N400 effects observed during the processing of verb-final sentences in German, Basque, and Hindi. By stacking Bayesian generalised additive models, we show that, in each language, N400 amplitudes and topographies in the region of the verb are best predicted when model-based surprisals are complemented by an Agent Preference principle that transiently interprets initial role-ambiguous noun phrases as agents, leading to reanalysis when this interpretation fails. Our findings demonstrate the need for this principle independently of usage frequencies and structural differences between languages. The principle has an unequal force, however. Compared to surprisal, its effect is weakest in German, stronger in Hindi, and still stronger in Basque. This gradient is correlated with the extent to which grammars allow unmarked NPs to be patients, a structural feature that boosts reanalysis effects. We conclude that language models gain more neurobiological plausibility by incorporating an Agent Preference. Conversely, theories of human processing profit from incorporating surprisal estimates in addition to principles like the Agent Preference, which arguably have distinct evolutionary roots.

The Effect of Indian Contact and Glaswegian Contact on the Phonetic Backward Transfer of Glaswegian English (L2) on Hindi and Indian English (L1)

This study examined phonetic backward transfer in ‘Glaswasians’, the ethnolinguistic minority of first-generation bilingual immigrant Indians in Glasgow (Scotland), who present a situation of contact between their native languages of Hindi and Indian English (L1s) and the dominant host language and dialect, Glaswegian English (L2). This was examined in relation to the Revised Speech Learning Model (SLM-r) and Speech Accommodation Framework. These predict that the migrants’ L1 sound categories can either shift to become more Glaswegian-like (‘assimilation’ or ‘convergence’) or exaggeratedly Indian-like (‘dissimilation’ or ‘divergence’) or remain unchanged. The effect of Indian and Glaswegian Contact on transfer was also investigated. Two control groups (Indians and Glaswegians) and the experimental group (Glaswasians) were recorded reading English and Hindi sentences containing multiple phones which were examined for multiple phonetic features (/t/—VOT, /l/—F2-F1 difference, /b d g/—Relative Burst Intensity). In both languages, Glaswasian /t/ and /g/ became more Glaswegian-like (assimilation), whereas F2-F1 difference in /l/ became exaggeratedly Indian-like (dissimilation). Higher Indian Contact was associated with more native-like values in /t/ and /l/ in Hindi but had no influence on /g/. Higher Glaswegian Contact was related to increased assimilation of /g/ in English but had no effect on /l/ and /t/.

Semantic Model for Fragment of Hindi (Part 1)

This paper proposes a formal model for syntactic and semantic analysis for the Hindi language using context-free grammar. In this paper, we developed a syntactic parser that generates syntactic trees for Hindi sentences based on rules of propositional logic, and gender conventions. The context-free rules we have written follow a top-down approach with a sentence that goes on self-arrangement. A set of experiments were run based on the corpus we have created, and significant results are presented in this paper. In addition to the above, the model characterizes lexical items in terms of individuals and sets for the syntactic distribution for well-formed formulas.

Development and Validation of the Emotion Laden Sentences Toolbox for Emotion Recognition (ELSTER).

Emotion recognition plays a crucial role in our social interactions and overall well-being. The present cross-sectional study aimed to develop and validate Emotion Laden Sentences Toolbox for Emotion Recognition (ELSTER), that utilizes emotion-laden sentences as stimuli to assess individuals' ability to perceive and identify emotions conveyed through written language. In Phase I, a comprehensive set of emotion-laden sentences in English language were validated by 25 (eight males and 17 females) qualified mental health professionals (MHPs). In Phase II, the sentences that received high interrater agreement in Phase I were selected and then a Hindi version of the same sentences was also developed. The English and Hindi database was then validated among 50 healthy individuals (30 males and 20 females). The percentage hit rate for all the emotions after exclusion of contempt was 84.3% with a mean kappa for emotional expression being 0.67 among MHPs. The percentage hit rate of all emotion-laden sentences across the database was 81.43% among healthy lay individuals. The mean hit rate percentage for English sentences was similar to Hindi sentences with a mean kappa for emotional expression being 0.63 for the combined English and Hindi sentences. The ELSTER database would be useful in the Indian context for researching textual emotion recognition. It has been validated among a group of experts as well as healthy lay individuals and was found to have high inter-rater reliability.

Locality and expectation effects in Hindi preverbal constituent ordering

We investigate the relative impact of two influential theories of language comprehension, viz., Dependency Locality Theory (Gibson, 2000; DLT) and Surprisal Theory (Hale, 2001; Levy, 2008), on preverbal constituent ordering in Hindi, a predominantly SOV language with flexible word order. Prior work in Hindi has shown that word order scrambling is influenced by information structure constraints in discourse. However, the impact of cognitively grounded factors on Hindi constituent ordering is relatively underexplored. We test the hypothesis that dependency length minimization is a significant predictor of syntactic choice, once information status and surprisal measures (estimated from n-gram i.e., trigram and incremental dependency parsing models) have been added to a machine learning model. Towards this end, we setup a framework to generate meaning-equivalent grammatical variants of Hindi sentences by linearizing preverbal constituents of projective dependency trees in the Hindi-Urdu Treebank (HUTB) corpus of written text. Our results indicate that dependency length displays a weak effect in predicting reference sentences (amidst variants) over and above the aforementioned predictors. Overall, trigram surprisal outperforms dependency length and parser surprisal by a huge margin and our analyses indicate that maximizing lexical predictability is the primary driving force behind preverbal constituent ordering choices in Hindi. The success of trigram surprisal notwithstanding, dependency length minimization predicts non-canonical reference sentences having fronted direct objects over variants containing the canonical word order, cases where surprisal estimates fail due to their bias towards frequent structures and word sequences. Locality effects persist over the Given-New preference of subject-object ordering in Hindi. Accessibility and local statistical biases discussed in the sentence processing literature are plausible explanations for the success of trigram surprisal. Further, we conjecture that the presence of case markers is a strong factor potentially overriding the pressure for dependency length minimization in Hindi. Finally, we discuss the implications of our findings for the information locality hypothesis and theories of language production.

Development of Automatic Rule-based Semantic Tagger and Karaka Analyzer for Hindi

Hindi is the third most-spoken language in the world (615 million speakers) and has the fourth highest native speakers (341 million). It is an inflectionally rich and relatively free word-order language with an immense vocabulary set. Despite being such a celebrated language across the globe, very few Natural Language Processing (NLP) applications and tools have been developed to support it computationally. Moreover, most of the existing ones are not efficient enough due to the lack of semantic information (or contextual knowledge). Hindi grammar is based on Paninian grammar and derives most of its rules from it. Paninian grammar very aggressively highlights the role of karaka theory in free-word order languages. In this article, we present an application that extracts all possible karakas from simple Hindi sentences with an accuracy of 84.2% and an F1 score of 88.5%. We consider features such as Parts of Speech tags, post-position markers (vibhaktis), semantic tags for nouns and syntactic structure to grab the context in different-sized word windows within a sentence. With the help of these features, we built a rule-based inference engine to extract karakas from a sentence. The application takes in a text file with clean (without punctuation) simple Hindi sentences and gives back karaka tagged sentences in a separate text file as output.

Cultural and Linguistic Adaptation of the Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) Into Hindi.

Aim The purpose of this study was to develop and assess the reliability of a Hindi version of the Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V). Reliability was assessed by comparing Hindi CAPE-V ratings with English CAPE-V ratings and by the Grade, Roughness, Breathiness, Asthenia and Strain (GRBAS) scale. Method Hindi sentences were created to match the phonemic load of the corresponding English CAPE-V sentences. The Hindi sentences were adapted for linguistic content. The original English and adapted Hindi CAPE-V and GRBAS were completed for 33 bilingual individuals with normal voice quality. Additionally, the Hindi CAPE-V and GRBAS were completed for 13 Hindi speakers with disordered voice quality. The agreement of CAPE-V ratings was assessed between language versions, GRBAS ratings, and two rater pairs (three raters in total). Pearson product-moment correlation was completed for all comparisons. Results A strong correlation (r > .8, p < .01) was found between the Hindi CAPE-V scores and the English CAPE-V scores for most variables in normal voice participants. A weak correlation was found for the variable of strain (r < .2, p = .400) in the normative group. A strong correlation (r > .6, p < .01) was found between the overall severity/grade, roughness, and breathiness scores in the GRBAS scale and the CAPE-V scale in normal and disordered voice samples. Significant interrater reliability (r > .75) was present in overall severity and breathiness. Conclusions The Hindi version of the CAPE-V demonstrates good interrater reliability and concurrent validity with the English CAPE-V and the GRBAS. The Hindi CAPE-V can be used for the auditory-perceptual voice assessment of Hindi speakers.

HiPHET: A Hybrid Approach to Translate Code Mixed Language (Hinglish) to Pure Languages (Hindi and English)

Bilingual code mixed (hybrid) languages has become very popular in India as a result of the spread of Western technology in the form of the television, the Internet and social media. Due to this increase in usage of code-mixed languages in day-to-day communication, the need for maintaining the integrity of Indian languages has arisen. As a result of this need the tool named Hinglish to Pure Hindi and English Translator was developed. The tool translated in three ways, namely, Hinglish to Pure Hindi and Pure English, Pure Hindi to Pure English and vice versa. The tool has achieved accuracy of 91% in giving Hindi sentences as output and of 84% in giving English sentences as output, where the input sentences were in Hinglish. The tool has also been compared with another similar tool in the paper.

Confusion analysis in phoneme based speech recognition in Hindi

Phoneme recognition is an essential step in the development of a speech recognition system (SRS), as phonemes are fundamental building blocks in a spoken language. This research work aimed to present phoneme recognition with systematic confusion analysis for the Hindi language. The accuracy of phoneme recognition is the foundation for developing an efficient SRS. Therefore, the systematic confusion analysis for phoneme recognition is essential to improve speech recognition performance. Experiments conducted on Continuous Hindi speech corpus for phoneme recognition with speaker-dependent mode using Hidden Markov Model (HMM) based tool kit HTK. Feature extraction technique Perceptual Linear Predictive Coefficient (PLP) was used with five states Monophones HMM model. Tests were performed for exploring the recognition of Hindi vowels and consonants. Confusion matrices were presented for both vowels and consonants with analysis and possible solutions. During systematic analysis, the vowels were divided into front, middle, and back vowels while consonants were categorized based on place of articulation and manner of articulation. Research findings show that some Hindi phonemes have significant effects on speech recognition. The investigations also reveal that some Hindi phonemes are mostly confused, and some phonemes have more deletions and insertions. The research further demonstrates that the words made of less number of phonemes show more insertion errors. It was also found that most of the Hindi sentences end with some specific words. These particular words can be used to reduce the search place in language modeling for improving speech recognition. The research findings can be utilized to enhance the performance of the speech recognition system by selecting suitable feature extraction techniques and classification techniques for phonemes. The outcome of the research can also be used to develop improved pronunciation dictionaries and designing the text for developing phonetically balanced speech corpus for improvement in speech recognition. Experimental results show an average corrected recognition score of 70% for vowel class and consonant categories, the maximum average corrected recognition score of 94% was obtained with palatal sounds, and the lowest average corrected recognition score of 54% was achieved with liquid sounds. The comparative analysis of the presented work was made to similar existing works.

Hindi Language Interface to Database

In our everyday lives we require information to accomplish daily tasks. Database is one of the most important sources of information. Database systems have been widely used in data storage and retrieval. However, to extract information from databases, we need to have some knowledge of database languages like SQL. But SQL has predefined structures and format, so it is hard for the non-expert users to formulate the desired query. To override this complexity, we have turned to natural language to retrieve information from database, which can be an ideal channel between a non-technical user and the application. But the application cannot understand natural language so an interface is required. This interface is capable of converting the user’s natural language query to an equivalent database language query. In this paper, we address the system architecture for translating a Hindi sentence in the form of an audio to an equivalent SQL query. The users don’t need to learn any formal query language; hence it’s easy to use for common people.

Children’s Story Classification in Indian Languages Using Linguistic and Keyword-based Features

The primary objective of this work is to classify Hindi and Telugu stories into three genres: fable, folk-tale, and legend . In this work, we are proposing a framework for story classification (SC) using keyword and part-of-speech (POS) features. For improving the performance of SC system, feature reduction techniques and combinations of various POS tags are explored. Further, we investigated the performance of SC by dividing the story into parts depending on its semantic structure. In this work, stories are (i) manually divided into parts based on their semantics as introduction, main, and climax ; and (ii) automatically divided into equal parts based on number of sentences in a story as initial, middle, and end . We have also examined sentence increment model, which aims at determining an optimum number of sentences required to identify story genre by incremental selection of sentences in a story. Experiments are conducted on Hindi and Telugu story corpora consisting of 300 and 150 short stories, respectively. The performance of SC system is evaluated using different combinations of keyword and POS-based features, with three well-established machine learning classifiers: (i) Naive Bayes (NB), (ii) k-Nearest Neighbour (KNN), and (iii) Support Vector Machine (SVM). Performance of the classifier is evaluated using 10-fold cross-validation and effectiveness of classifier is measured using precision, recall, and F-measure. From the classification results, it is observed that adding linguistic information boosts the performance of story classification. In view of the structure of the story, main, and initial parts of the story have shown comparatively better performance. The results from the sentence incremental model have indicated that the first nine and seven sentences in Hindi and Telugu stories, respectively, are sufficient for better classification of stories. In most of the studies, SVM models outperformed the other models in classification accuracy.

LSTM Based Lip Reading Approach for Devanagiri Script

Speech Communication in a noisy environment is a difficult and challenging task. Many professionals work in noisy environments like aviation, constructions, or manufacturing, and find it difficult to communicate orally. Such noisy environments need an automated lip-reading system that could be helpful in communicating some instructions and commands. This paper proposes a novel lip-reading solution, which extracts the geometrical shape of lip movement from the video and predicts the words/sentences spoken. An Indian specific language data set is developed which consists of lip movement information captured from 50 persons. This includes students in the age group of 18 to 20 years and faculty in the age group of 25 to 40 years . All have spoken a paragraph of 58 words within 10 sentences in Hindi (Devanagari, spoken in India) language which was recorded under various conditions. The implementation consists of facial parts detection, along with Long short term memory’s. The proposed solution is able to predict the words spoken with 77% and 35% accuracy for data set of 3 and 10 words respectively. The sentences are predicted with 20% accuracy, which is encouraging.

Supervised Word Sense Disambiguation using Decision Tree

Semantic processing is an essential task in natural language processing. In semantic processing it has observed that some words have more than one meaning. Multiple meanings of a word create serious problems to linguists which produces ambiguity in sentence. Word Sense Disambiguation is one of the main challenges in natural language processing which is present in almost all the languages. By existing knowledge and experience human can certainly disambiguate the words but for machine it is difficult task. In the proposed work, we are resolving the ambiguity of all open class word in English sentence and translating it to the Hindi sentence. We have used decision tree as a classifier. For improving the speed of translation we have used the concept of translation memory.

Speaker identification and its application in automobile industry for automatic seat adjustment

In this paper, an application of speaker identification in automobile industry is proposed. The work is divided into two main categories. The first part deals with the task of speaker identification where a system is trained and tested for multiple users using a database of isolated Hindi digits and Hindi sentences. A hybrid new algorithm is used for speaker identification which captures the benefits of both LPC and MFCC feature extraction technique. The new proposed technique shows an improvement of 2.05% over conventional MFCC features for isolated Hindi digits and 12.41% for Hindi sentences. It also shows an improvement of 53.26 over LPC for Hindi sentence and 32.51% for isolated Hindi digit over LPC. The proposed features were also tested for real time noisy environment by adding speech and F16 noise to test voice samples with varying degree of distortion starting from 0 to 20 dB. The second part describes the interfacing techniques and design of the hardware configuration for seat adjustment. The proposed model is designed using MATLAB. Speech samples from users are recorded through a microphone. Different features of this wav file are evaluated and fed into the model generated during testing phase. Depending on outcome from the classifier, a user is identified. Once the user is successfully identified, signals are sent to the servo motor through arduino microcontroller interfaced through MATLAB to automatically adjust the driver’s seat.

A probabilistic feature based SVM model for Hindi/English speech recognition

Real time speech recognition has various challenges including noise, turbulence, language and crosstalk problem. In this paper, multi-phase hybridization is applied to cover these challenges and to provide effective speech recognition. The model is explicitly divided into three main stages where each stage is implicitly divided into several sub-stages to provide specific problem solution. The proposed hybrid model resolved the problem of acoustic turbulence, background noise and instrumentation noise problem at the earlier stage. The rectified speech signals are processed using ICA and Fuzzy-HMM approach to generate the structural and statistical features. In this stage, the signal is divided in smaller linear blocks to extract the features. Later on, fuzzy-weighted SVM is implied to recognize the speech signal. The experimentation is applied on Hindi and English characters and sentence datasets. The comparative results are derived against BPNN and PCA models for different sample sets. The comparative results obtained from model signifies that the model has improved the recognition rate effectively.

Relation of musical experience to perceiving and producing aspirated Hindi consonants

Past research shows that those with musical experience often perceive and produce unfamiliar speech contrasts better than non-musicians (e.g., Gottfried, 2007; Lee & Hung, 2008; Marie, Delogu, Lampis, Belardinelli, & Besson, 2011; Slevc & Miyake, 2006). The present research seeks to clarify the mechanisms which underlie this relationship through a “test-teach-test” paradigm (see Vlahou, Protopapas, & Seitz, 2012). In the first session, native speakers of American English with and without conservatory training were tested on their discrimination of Hindi sentences that contained either an aspirated (e.g., [bh]) or unaspirated (e.g., [b]) consonant (“test”). In a second session, participants completed training on producing and perceptually discriminating the aspirated and unaspirated Hindi consonants (“teach”). In the third session, participants were tested on their ability to perceive and to produce these unfamiliar consonants in the same and different phonetic contexts (“test”). Preliminary results suggest that all participants benefited from the training, but Improvement was markedly greater for musicians than for non-musicians. Current studies are further testing additional musicians and non-musicians to evaluate the extent which musical experience influences perception and production of these unfamiliar Hindi phonemes.Past research shows that those with musical experience often perceive and produce unfamiliar speech contrasts better than non-musicians (e.g., Gottfried, 2007; Lee & Hung, 2008; Marie, Delogu, Lampis, Belardinelli, & Besson, 2011; Slevc & Miyake, 2006). The present research seeks to clarify the mechanisms which underlie this relationship through a “test-teach-test” paradigm (see Vlahou, Protopapas, & Seitz, 2012). In the first session, native speakers of American English with and without conservatory training were tested on their discrimination of Hindi sentences that contained either an aspirated (e.g., [bh]) or unaspirated (e.g., [b]) consonant (“test”). In a second session, participants completed training on producing and perceptually discriminating the aspirated and unaspirated Hindi consonants (“teach”). In the third session, participants were tested on their ability to perceive and to produce these unfamiliar consonants in the same and different phonetic contexts (“test”). Preliminary results sugges...

Speech enhancement using Teager energy operated ERB-like perceptual wavelet packet decomposition

In recent past, wavelet packet (WP) based speech enhancement techniques have been gaining popularity due to their inherent nature of noise minimization. WP based techniques appeared as more robust and efficient than short-time Fourier transform based methods. In the present work, a speech enhancement method using Teager energy operated equal rectangular bandwidth (ERB)-like WP decomposition has been proposed. Twenty four sub-band perceptual wavelet packet decomposition (PWPD) structure is implemented according to the auditory ERB scale. ERB scale based decomposition structure is used because the central frequency of the ERB scale distribution is similar to the frequency response of the human cochlea. Teager energy operator is applied to estimate the threshold value for the PWPD coefficients. Lastly, Wiener filtering is applied to remove the low frequency noise before final reconstruction stage. The proposed method has been applied to evaluate the Hindi sentences database, corrupted with six noise conditions. The proposed method’s performance is analysed with respect to several speech quality parameters and output signal to noise ratio levels. Performance indicates that the proposed technique outperforms some traditional speech enhancement algorithms at all SNR levels.

Web Recognition of Spoken Hindi

Technology has evolved and computers have but still Indian communities are far from the use of computers, only 37% [13] user of Indian society like persons from academics, health, engineering and research make use of the benefits of computer. Although there is a revolution in development of operating systems in the past two years, there are no operating systems that support Indian languages like Hindi, they only support English language and people who know English can work on these. This work shows the development of speaker independent ASR system for Indian speaker of a particular type i.e. spoken Hindi. Objective: An automated system is developed which accept Hindi query from the user and search the keywords from the query on web and shows the result accordingly. A bilingual lexicon of 3145 words was built. The techniques to convert acoustic speech signals into strings of words were also designed. The dictionary maintains the POS of source to target language and CFG grammar based model for Hindi language was developed. Methods: A speech database consisting of speech files is created at the rate of 16 KHz. Interviews were conducted uto record speech files from users for developing the speech database for training the system. The system takes spoken Hindi as input and generates Hindi sentences. Hindi sentences are parsed with the help of Top-Down Paser and identify the keywords and form a exact query with the help of grammar rules which are given as input to Google search engine to search the result as per query and display on screen. The lexical categories of Hindi language in grammar are done on the bases of verb, noun, preposition, adjective, adverb phrases. Result: A total of 101 speakers from Faridabad district, comprising of both males and females took part in data collection process. The system was tested in a sound proof room and achieved 88.05% accuracy. It is observed that utilization of more training data together with detailed modeling of speech signals can improve the system performance to a level adequate for actual deployment. Application/Improvements: This system provides access to a computer system or to digital content over the internet to illiterate, vision-impaired, urban and semi-urban Indian people who are not able to read/write English language. The same speech interface can be enhanced to work in other regional languages of India like Punjabi, Marathi and Telugu, etc. To enhance or to extend it for other languages, the transfer or translation rules of grammar is needed, which can be generated with great ease by using the same dataset with different target languages. Keywords: Corpus, Hindi, Recognition, Speech, Web

A Novel Approach to Paraphrase Hindi Sentences using Natural Language Processing

Background/Objectives: Nowadays, most of the automatic work has been done in English language but not much work has been done in Hindi language. The main objective is to convert the existing sentence in different form by remaining the semantic or meaning same. This will helpful in converting the complex sentence into simpler one.Methods/Statistical Analysis:Our system mainly deals with Hindi Sentences and its different forms. It takes a sentence as input and produces another sentence without changing its semantic after applying synonyms and antonyms replacement method.Findings:Reframing of Hindi sentences can be used to change a complex sentence in simplified form.The system is implemented in java. WampServer is used as database for our system. In our paper, we have described complete algorithm to paraphrase the sentences. The performance of the system is totally dependent on the size of Database. Application/Improvements:This application can be helpful in designing robots to understand different forms of Hindi sentences, to use as Hindi tutor for students to get them idea about different form of sentences and in plagiarism tools to find the higher level of plagiarized text up to certain extent. The test results have been verified by various tutors.

The Left, The Better: White-Matter Brain Integrity Predicts Foreign Language Imitation Ability.

Speech imitation is crucial for language acquisition and second-language learning. Interestingly, large individual differences regarding the ability in imitating foreign-language sounds have been observed. The origin of this interindividual diversity remains unknown, although it might be partially explained by structural predispositions. Here we correlated white-matter structural properties of the arcuate fasciculus (AF) with the performance of 52 German-speakers in a Hindi sentence- and word-imitation task. First, a manual reconstruction was performed, permitting us to extract the mean values along the three branches of the AF. We found that a larger lateralization of the AF volume toward the left hemisphere predicted the performance of our participants in the imitation task. Second, an automatic reconstruction was carried out, allowing us to localize the specific region within the AF that exhibited the largest correlation with foreign language imitation. Results of this reconstruction also showed a left lateralization trend: greater fractional anisotropy values in the anterior half of the left AF correlated with the performance in the Hindi-imitation task. From the best of our knowledge, this is the first time that foreign language imitation aptitude is tested using a more ecological imitation task and correlated with DTI tractography, using both a manual and an automatic method.