Parminder Singh

Text-To-Speech Synthesis System for Punjabi Language

A Text-To-Speech (TTS) synthesis system has been developed for Punjabi text written in Gurmukhi script. Concatenative method has been used to develop this TTS system. Syllables have been reported as good choice of speech unit for speech databases of many languages. Since Punjabi is a syllabic language, so syllables has been selected as the basic speech unit for this TTS system, which preserves within unit co-articulation effects. The working of this Punjabi TTS system can be divided into two modules: Online Process and Offline Process. Online process is responsible for pre-processing of the input text, schwa deletion, syllabification and then searching the syllables in the speech database. Pre-processing involves the expansion of abbreviations, numeric figures and special symbols etc. Schwa deletion is an important step for the development of a high quality Text-To-Speech synthesis system. Phonetically, schwa is a very short neutral vowel sound, and like all vowels, its precise quality varies depending on the adjacent consonants. During utterance of words not every schwa following a consonant is pronounced. In order to determine the proper pronunciation of words, it is necessary to identify which schwas are to be deleted and which are to be retained. Grammar rules, inflectional rules and morphotactics of language play important role for identification of schwa those are to be deleted. A rule based schwa deletion algorithm has been developed for Punjabi having accuracy of about 98.27%. Syllabification of the words of input text is also a challenging task. Defining a syllable in a language is a complex task. There are many theories available in phonetics and phonology to define a syllable. In phonetics, syllables are defined based upon the articulation. However in phonological approach, syllables are defined by the different sequences of the phonemes. In every language, certain sequences of phonemes are recognized. In Punjabi seven types of syllables are recognized – V, VC, CV, VCC, CVC, CVCC and CCVC (where V and C represents vowel and consonant respectively), which combine in turn to produce words. A syllabification algorithm for Punjabi has been developed having accuracy of about 96.7%, which works on the output of the schwa deletion algorithm.

Review of Machine Transliteration Techniques

is the conversion of a text from one script to another, and thus representing words from one language using the approximate phonetic or spelling equivalents of another language. Machine Transliteration has come out to be an emerging and a very important research area in the field of machine translation. Transliteration systems are very beneficial for removing the language and scriptural barriers. It has gained prime importance as a supporting tool for machine translation and cross-language information retrieval, especially when proper names and technical terms are involved. Various techniques are available for transliteration process. This paper is intended to give a brief overview of commonly used machine transliteration techniques.

A Rule Based Schwa Deletion Algorithm for Punjabi TTS System

Phonetically, schwa is a very short neutral vowel sound, and like all vowels, its precise quality varies depending on the adjacent consonants. During utterance of words not every schwa following a consonant is pronounced. In order to determine the proper pronunciation of words, it is necessary to identify which schwas are to be deleted and which are to be retained. Schwa deletion is an important step for the development of a high quality Text-To-Speech synthesis system. This paper specifically describes the schwa deletion rules for Punjabi written in Gurmukhi script. Performance analysis of the implemented rule based schwa deletion algorithm, evaluates its accuracy to be 98.27%.

Festival Framework for Synthesis of Punjabi Voice

Speech generation is process of converting the text to speech called TTS system. This paper presents the generation of Punjabi waveform by using Festival framework. Building of new voice is done through support of Festvox, Festival and Speech Tools. Festival acts as an Engine for waveform synthesis and statistical parametric synthesis method is implemented for building Punjabi voice. The required data for building the voice is recorded in the noiseless environment and maximum Punjabi valid phonemes are covered in the corpus. Text Processing is done to collect the nice prompts to build the accurate voice Model. The accuracy factor is calculated through Mel-cepstral distortion (MCD) parameters.

Punjabi Dialects Conversion System for Majhi, Malwai and Doabi Dialects

In todays modern era of technology, more number of people use internet for the purpose of expressing their opinions, thoughts and ideas through social media as well as articles. This leads to increased informal text available for public access. Such text may also be available in different dialectal forms of the specific language and may attract natives of that region. Moreover, literature, local news, articles, etc. written in a particular dialectal form of language is more expressive. For this purpose, dialect conversion systems plays vital role. This paper describes the dialect conversion system for Punjabi language that converts input text to either of three Punjabi dialects namely Majhi, Malwai and Doabi. A rule based approach is adopted for defining the conversion rules and bilingual dictionary is also used for this purpose.

Hindi to Punjabi Transliteration using Phonetic and Orthographic Rules

One of the important applications of Natural Language Processing is machine translation. Machine transliteration is an emerging and a very important research area in the field of machine translation. Translation systems translate message from source language to target language, keeping the exact meaning. While the transliteration system finds the same meaning word/sentence in another language, the transliteration helps us to pronounce them. This paper addresses the transliteration process from Hindi to Punjabi language using a rule based approach. Transliteration is more phonetic process, thus both source grapheme and its sound in the correct pronunciation of word have been considered for rule formation to achieve high performance and more accurate results. The system is tested on news domain text and achieved accuracy of 97%.

Object based Accountability Framework for Information Sharing in Cloud Computing

Cloud computing is one of the biggest thing in computing in recent time. Cloud computing uses the internet and the central remote servers to support different data and applications. Cloud computing is that emerging technology which is used for providing various computing and storage services over the Internet. In the cloud computing, the internet is viewed as a cloud. Internet users can receive services from a cloud as if they were employing a super computer which be using cloud computing. Accountability is one of the major reforms that are provided in cloud environment. Because of this we can restrict the use of the user information by the third party. The user is pre informed when his or her information is shared with some third party or any organization. The accountability provides the uses the Object oriented approach for holding all that information. The information is shared with the concerned user prior to the misuse of that information To Whom It May Concern. The study also focuses on web application framework to enhance the security of cloud computing.

Optimization of Tasks in Mobile Cloud Computing

cloud computing is a new platform for the execution of mobile applications where cloud performs the stimulating computing-intensive tasks and storing data in place of the mobile devices and provides them an illusion of infinite computing resources. This research work considers a cloud based mobile computing system consisting of virtual machines (as resources), cloudlets (as requests) and broker, where the broker assigns user cloudlet requests to virtual machines to be processed by the servers. It has been a great challenge to design and build an effective load balancing algorithm for the broker which spreads the service request load on virtual machines while utilizing the resources to the maximum. In this paper, a scheduling model to optimize the load based on maximum resource utilization rate using genetic algorithm for scheduling requests is proposed where the computing capacity of a datacenter is divided into number of tiers. Simulation results shows that the proposed work can effectively cope with the load imbalance problem in mobile cloud computing. KeywordsBalancing, Cloudlets, Virtual Machines, Response Time.

Automatic marking of Punjabi syllables boundaries in a sound file

Automatic Speech segmentation is one of the foremost important field for controlling the simulation of speech without intervening of human being. Segmenting the continuous speech signal according to the phonetic transcription is a fundamental task in any voice activated system. Manual segmentation is tedious, time consuming and error prone. Automatic segmentation is not faultless, but it is inherently consistent and results are reproducible. In spite of the endless efforts made in this field, there is no Speech Segmentation System in the market for Punjabi on large vocabulary, though speaker independent systems are available for the languages like English, Tamil. It is a well known fact Syllable based systems perform better than phoneme or word based systems. In our work, we are presenting an effective method for segmentation of Punjabi Speech into syllable like Basic units for ASR systems.