Analysis of Inter-Pausal Units in Indian Languages and Its Application to Text-to-Speech Synthesis

Prakash, Jeena J.; Murthy, Hema A.

doi:10.1109/taslp.2019.2924534

Cited by 10 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Peng et al [19] have presented a deep semantic approach over multiple perspectives in order to extract the correlation between two sentences. Prakash and Murthy [20] have presented a language specific approach for improving the performance of text-to-speech application. Quan et al [21] have used a tree-based integrated structure in order to find similarity between two given sentences.…”

Section: A Backgroundmentioning

confidence: 99%

Modelling Simple and Efficient Data Transformation Scheme for Improving Natural Language Processing

J*,

Swamy

2020

IJITEE

View full text Add to dashboard Cite

The importance of natural language processing cannot be sided in the current era of communication and analytics where data is exponentially growing. Although, there has been various versions and schemes that has evolved in the past decade towards improving the performance of natural language processing, but still the problem towards precisely extracting the actual context is an open ended. Review of existing studies show a large scope of new work towards improving it. Therefore, this manuscript presents a unique simplified approach where natural language processing is carried out with a combined effort of syntactical and semantic based transformation scheme. The study is implemented using analytical methodology while the secondary motive of the work is also to balance the mining performance as well as optimizing storage performance too. The study outcome shows proposed scheme to excel better performance with respect to time duration in all the internal processes being involved for data transformation.

show abstract

Section: A Backgroundmentioning

confidence: 99%

Modelling Simple and Efficient Data Transformation Scheme for Improving Natural Language Processing

J*,

Swamy

2020

IJITEE

View full text Add to dashboard Cite

show abstract

“…Indian languages, in its written form, inherently lack punctuation marks other than sentence endings, and use manually and artificially inserted punctuation marks in modern writing (Bellur et al, 2011; Vadapalli et al, 2013). This is due to the fact that Indian languages are phrase‐based in terms of production and perception (Féry, 2010; J.J. Prakash & Murthy, 2019). Hence, much of the punctuation prediction research for these languages are mapped to phrase‐break prediction task (i.e., predicting the presence or absence of a break) predominantly for improving the naturalness of synthetic speech in speech synthesis systems (Vadapalli et al, 2013; Sarkar & Rao, 2015; A. Prakash et al, 2016; J.J. Prakash & Murthy, 2019).…”

Section: Introductionmentioning

confidence: 99%

“…This is due to the fact that Indian languages are phrase‐based in terms of production and perception (Féry, 2010; J.J. Prakash & Murthy, 2019). Hence, much of the punctuation prediction research for these languages are mapped to phrase‐break prediction task (i.e., predicting the presence or absence of a break) predominantly for improving the naturalness of synthetic speech in speech synthesis systems (Vadapalli et al, 2013; Sarkar & Rao, 2015; A. Prakash et al, 2016; J.J. Prakash & Murthy, 2019). Since Indian languages are syllable‐timed (A. Prakash et al, 2016), much of the previous research involving phrase‐break prediction (predominantly for speech synthesis systems) revolve around syllabic features.…”

Section: Introductionmentioning

confidence: 99%

“…Hence, much of the punctuation prediction research for these languages are mapped to phrase-break prediction task (i.e., predicting the presence or absence of a break) predominantly for improving the naturalness of synthetic speech in speech synthesis systems (Vadapalli et al, 2013;Sarkar & Rao, 2015;A. Prakash et al, 2016; J.J. Prakash & Murthy, 2019). Since Indian languages are syllable-timed (A.…”

mentioning

confidence: 99%

“…The CART-based pause prediction using text-level features resulted in a maximum F1-score of 0.75 for Hindi (Sarkar & Rao, 2015), and lower scores (in the range of 0.24-0.62) for other Indian languages such as, Tamil and Telugu (Vadapalli et al, 2013). In J.J. Prakash and Murthy (2019), gamma distributions on inter-pausal units extracted from speech signals are modelled using Viterbi algorithm. This phrasing system reports precision scores of 0.892, 0.89, 0.835, and 0.639, to predict phrase-breaks in Hindi, Tamil, Telugu, and Malayalam, respectively.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Feature‐weightedAdaBoostclassifier for punctuation prediction in Tamil and HindiNLPsystems

2021

View full text Add to dashboard Cite

Punctuation marks play a vital role in text representation and interpretation, and are useful in enhancing the performance of modern Natural Language Processing (NLP) systems such as voice input typing aids, machine translation, and speech synthesis systems. Punctuation marks, except period, are inherently not available in Indian languages such as Tamil and Hindi. However, some modern forms of writing such as news articles, blogs, stories, and so forth, incorporate user‐defined punctuation marks in these languages. The current work proposes an automatic punctuation prediction system for texts in Tamil and Hindi using classification approach, where punctuation prediction is considered as a multi‐class classification problem. Word‐level text features are chosen and are analysed to validate their language‐dependency and significance towards punctuation prediction. A Feature‐weighted AdaBoost (FAda) classifier is proposed that defines a novel boosting factor to adjust the hypothesis weight of the weak classifiers, hence reducing the number of false classifications. It is observed that the proposed classifier outperforms the other classification techniques such as, AdaBoost, SVM, CART, CRF, and Bi‐LSTM by a maximum difference of 50% and 16% in the macro F1‐scores for Tamil and Hindi texts, respectively. The proposed classifier performs on par with the attention‐based classifier for both Tamil and Hindi texts. Further, as a proof of concept, the proposed punctuation prediction system is applied to voice keyboard, machine translation, and speech synthesis systems, to validate the effect of the punctuation marks on the performance of these Natural Language Processing (NLP) systems.

show abstract

Simplified Framework of Natural Language Processing for Structure Management of Current-Age Data

Shruthi¹,

Swamy²

2020

Intelligent Algorithms in Software Engineering

View full text Add to dashboard Cite

Analysis of Inter-Pausal Units in Indian Languages and Its Application to Text-to-Speech Synthesis

Cited by 10 publications

References 36 publications

Modelling Simple and Efficient Data Transformation Scheme for Improving Natural Language Processing

Modelling Simple and Efficient Data Transformation Scheme for Improving Natural Language Processing

Feature‐weightedAdaBoostclassifier for punctuation prediction in Tamil and HindiNLPsystems

Simplified Framework of Natural Language Processing for Structure Management of Current-Age Data

Contact Info

Product

Resources

About