Text to speech synthesis system for mobile applications,

Speech is used to express information, emotions, and feelings. Speech synthesis is the technique of converting given input text to synthetic speech. Speech synthesis can be used to read text as in SMS, newspapers, site information etc. and can be used by blind people. Speech synthesis has been widely researched in last four decades. The quality and intelligibility of the synthetic speech produced is remarkably good for most of the applications. This report intends to review four majorly researched methods of speech synthesis viz. Articulatory, Concatenated, Formant, and Quasi-articulatory Synthesis. Mainly in this paper focus is given on concatenate synthesis method and some issues of this method are discussed. Articulatory Synthesis is based on human speech production model. The synthetic speech produced by this model is most natural, but it is also the most difficult method. Concatenate Synthesis uses prerecorded speech words, phrases and concatenates them to produce sound. It is the simplest method and yields high-quality speech but is limited by its memory requirement to store beforehand all possible words, phrases to be produced. Formant Synthesis is based on the acoustic model of the human speech production system. It models the sound source and the resonance in the vocal tract, and is most common model used. Quasi-articulatory Synthesis is a hybrid of articulator acoustic model of speech production. Synthetic speech produced by this model sounds more natural and can be easily customized to meet different requirements of different applications and individual users.

2005

This project is concerned with the development of a Text to Speech (TTS) solution for mobile telephony services in the local context, where citizens share both Maltese and English as their primary languages. The input domain under focus is that of SMS messages and, while attention is given to input TTS issues for Maltese, the influence of the second language is taken into consideration.

Different Bengali TTS systems are already available on a resourceful platform such as a personal computer. However, porting these systems to a resource limited device such as a mobile phone is not an easy task. Practical aspects including application size and processing time have to be concerned. This paper describes the implementation of a Bengali speech synthesizer on a mobile device. For speech generation we used Epoch Synchronous Non Overlap Add (ESNOLA) based concatenative speech synthesis technique which uses the partnemes as the smallest signal units for concatenations.

Speech Synthesis is one of the most leading application areas in natural language processing (NLP). This is also known as “Text-To-Speech” (TTS) and is mainly the capability of the device to “speak” text of different languages. This application acts as an interface between two different representations of information, namely text and speech, to perform effective communication between two parties. Our main objective is to make an application of speech synthesis for Android based mobile phones. We have developed an application on the Android environment and the voice conversion libraries provided by Android environment are used. The application developed is user friendly and reliable and effective communication is performed.

A text-to-speech (TTS) synthesizer is a computer based system that should be able to read any text aloud. Most text-to-speech synthesis lacks naturalness and intelligibility. This study is aimed at achieving the ease with which the output is understood and how closely the output sounds like human speech referred to as intelligibility and naturalness. In this research, an algorithm is developed in C-programming language capable of recognizing 50 isolated English vocabularies and produces the corresponding sound output using concatenative technique which employs natural human voice and produces the most natural-sounding speech. The vocabularies used as inputs were pre-recorded in .wav format and stored in the database. A user input the text which is searched through the database and the corresponding sound is played if a match is found otherwise an error message is given to check your spelling and try again

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.

International Standards Publication -ISP, 2014

Speech is used to convey information, emotions, and feelings. Speech synthesis is the technique of converting given input text to synthetic speech. Speechsynthesis can be used to read text as in SMS, newspapers, site information etc. and can be used by blind people. Speech synthesis has been widely researched in last four decades. The quality andintelligibility of the synthetic speech produced is remarkably good for most of the applications. This report intends to review four majorly researched methods of speech synthesis viz. Articulatory, Concatenated, Formant, and Quasi-articulatory Synthesis. Mainly in this paper focus is given on Concatenative synthesismethod and some issues of this method are discussed. Articulatory Synthesis is based on human speech production model. The synthetic speech produced by this model is most natural, but it is also the most difficult method. Concatenative Synthesis uses prerecorded speech words, phrases and concatenates them to produce sound. It is the simplest method and yields high-quality speech but is limited by its memory requirement to store beforehand allpossible words, phrases to be produced. Formant Synthesis is based on the acoustic model of the human speech production system. It models the sound source and the resonance in the vocal tract, and is most common model used. Quasi-articulatory Synthesis is a hybrid of articulator acoustic model of speech production. Synthetic speech produced by this model sounds more natural and can be easily customized to meet different requirements of different applications and individualusers.

2001

This paper deals with the design of a speech corpus for a concatenation-based text-to-speech (TTS) synthesis. Several aspects of the design process are discussed here. We propose a sentence selection algorithm to choose sentences (from a large text corpus) which will be read and stored in a speech corpus. The selected sentences should include all possible triphones in a sufficient number of occurrences. Some notes on recording the speech are also discussed to ensure a quality speech corpus. As some popular speech synthesis techniques require knowing the moments of principal excitation of vocal tract during the speech, pitch-mark detection is also a subject of our attention. Several automatic pitch-mark detection methods are discussed here and a comparison test is performed to find out the best method.

In the modern era of information technology, information is carried out in various ways to lead human life easily. Information can be exchanged among people in various ways and speech is the primary communication process among human beings. A TTS (Text-to-Speech) is used to convert input text to speech, and it’s very popular application for computer users. Although different types of speech synthesis technologies are available for the English, France, Chinese and so many other languages, but in Bengali language, it’s so scarce. This paper represents the implemented process of training based Concatenative Bangle Speech Synthesizer System and its performance. The synthetic utterances are built by concatenating different speech units selected from recorded database from the training session for concatenative speech synthesizer system. Here training based means any person can train his/her voice and that will be stored on database and next time that person will input a text to convert speech and listen according to his/her trained voice. So this process is known as independent voice. And to train the voice a set of Bengali keyword is stored on the database as segmented audio file. At last the performance of this Bangla speech synthesizer system implemented by the concatenative speech synthesizer technology is analyzed which has provided 85% accuracy to listener to identify the sentence.