Developing a Child Friendly Text-to-Speech System

Proceedings of the Meeting on English Language Teaching (MELT) 2015

There has been an increasing amount of research on the use of technology in second language (L2) education. Among the wide range of topics in the field of computer-assisted language learning, text-to-speech synthesizers (TTS) have piqued the interest of many researchers for their potential to enhance the L2 acquisition of writing (Kirsten, 2006), vocabulary and reading (Proctor, Dalton & Grisham, 2007) and pronunciation (Cardoso, Collins & White, 2012; Soler-Urzua, 2011). Despite its proven effectiveness, very few formal evaluations of TTS have been conducted, and those that exist are somewhat dated (the latest found was Kang, Kashiwagi, Treviranus, & Kabugiri, 2009). The present study was an attempt to evaluate the language learning potential of an up-to-date TTS system according to four criteria constituting speech quality (comprehensibility, naturalness, accuracy, and intelligibility). Participants listened to and rated both human- and TTS-produced stories and sentences on a 6-point scale. Results of paired samples t-tests indicated that though the human samples earned higher ratings than the TTS samples, the speech quality of the TTS system used was considered high enough to justify its readiness for use in language learning activities. The discussion of the findings will highlight how TTS technology can be used to complement and enhance the teaching of L2 pronunciation and other linguistic skills both inside and outside the classroom.

Speech is one of the oldest and most natural means of information exchange between human. Over the years, Attempts have been made to develop vocally interactive computers to realise voice/speech synthesis. Obviously such an interface would yield great benefits. In this case a computer can synthesize text and give out a speech. Text-To-Speech Synthesis is a Technology that provides a means of converting written text from a descriptive form to a spoken language that is easily understandable by the end user (Basically in English Language). It runs on JAVA platform, and the methodology used was Object Oriented Analysis and Development Methodology; while Expert System was incorporated for the internal operations of the program. This design will be geared towards providing a one-way communication interface whereby the computer communicates with the user by reading out textual document for the purpose of quick assimilation and reading development.

1997

2010

The goal of this paper is to provide a short but comprehensive overview of text-to-speech synthesis by highlighting its natural language processing (NLP) and digital signal processing (DSP) components. First, the front-end or the NLP component comprised of text analysis, phonetic analysis, and prosodic analysis is introduced then two rule-based synthesis techniques (formant synthesis and articulatory synthesis) are explained. After that concatenative synthesis is explored. Compared to rulebased synthesis, concatenative synthesis is simpler since there is no need to determine speech production rules. However, concatenative synthesis introduces the challenges of prosodic modification to speech units and resolving discontinuities at unit boundaries. Prosodic modification results in artifacts in the speech that make the speech sound unnatural. Unit selection synthesis, which is a kind of concatenative synthesis, solves this problem by storing numerous instances of each unit with varying prosodies. The unit that best matches the target prosody is selected and concatenated. Finally, hidden Markov model (HMM) synthesis is introduced.

This project will present an application focused on the teaching of the English language to the children, this application being an important teaching tool, where the child can begin a cycle of learning a new language, something that will be very important in their training academic, and will serve in your professional future. In addition to showing how software is being developed and the resources used in it, this project is also concerned with presenting concepts such as: foreign language learning for children, voice recognition and synthesis, intelligent systems capable of recognizing and synthesizing the voice and the Java API Speech. To aid in English studies, the application makes use of illustrative images, themes, interactive questions, training mode, speech recognition and synthesis, which contributes to the development of writing and pronunciation in the language, mainly for making use of the resources of voice, which are the strongest point of this tool.

International Journal of …, 2002

This paper explores technology available for prototyping and product development of child speech recognition applications, and factors relevant for eventual delivery of good user experience. Since child voices are known to be more challenging than adults, and less ...

2015

Speech is the most innate and fastest means of communication between humans. Computers with the ability to understand speech and speak with a human like voice are expected to contribute to the development of more natural man-machine interface. For the analysis of speech signal we have carried out the recording of six children speakers (3 male and 3 female) in Dogri language between the age group of 3-6 years. Harmonic plus noise model HNM has been employed as the analysis-synthesis platform as it outperforms almost all models of speech production in terms of important characteristics like naturalness, intelligibility, and pleasantness. PESQ method is used for evaluation of the quality of the speech synthesized from HNM. Mean and standard deviation (SD) is estimated for original and synthesized speech. Effect of different proportion of voice part on the quality and intelligibility of speech signal of children has been investigated at different levels of noise keeping noise part const...

The most common, easy and feasible ways of communication is speech. Due to wide range of applications and physically disabled people requires an application to convert text to speech. Now a days Gujarati language is also widely used as a communication medium. Many systems has been developed so far to convert text to speech with one or more limitations. This review paper includes overview about text to speech systems developed for Gujarati language. The techniques to develop speech synthesizer are included. All individual technique is having limitations. So, to overcome these limitations, methodology is provided to develop a hybrid synthesizer for text to speech conversion for Gujarati Language. As a result, A good speech synthesizer achieves two quality measures of text to speech system: Naturalness and Intelligibility. The produced speech than pass through Super position algorithm developed using Formant Synthesizer and Timedomain Synthesizer to achieve more prosody on output and synthesized speech.