Text To Speech System Research Articles

Text Normalization and Diphone Preparation for Bangla Speech Synthesis

This paper presents methodologies involved in text normalization and diphone preparation for Bangla Text to Speech (TTS) synthesis. A Concatenation based TTS system comprises basically two modules- one is natural language processing and the other is Digital Signal Processing (DSP). Natural language processing deals with converting text to its pronounceable form, called Text Normalization and the diphone selection method based on the normalized text is called Grapheme to Phoneme (G2P) conversion. Text normalization issues addressed in this paper include tokenization, conjuncts, null modified characters, numerical words, abbreviations and acronyms. Issues related with diphone preparation include diphone categorization, corpus preparation, diphone labeling and diphone selection. Appropriate rules and algorithms are proposed to tackle all the above mentioned issues. We developed a speech synthesizer for Bangla using diphone based concatenative approach which is demonstrated to produce much natural sounding synthetic speech.

A novel prosody adaptation method for Mandarin concatenation-based text-to-speech system

The paper presents a prosody adaptation method which is able to adapt the prosody model of text to speech (TTS) to a new style with a small training corpus. Unlike the conventional prosody mapping between two parallel prosody features, the paper tries to integrate the prosody conversion into the prosody generation model of TTS. In the paper, we use a template-based prosody model which consists of two major parts: the prosody template library and the template parameter prediction trees for TTS system. With this model, the prosody adaptation is realized by the following two steps: converting the prosody template library to the target speaker’s prosody based on the mapping methods, re-training prosody prediction trees with the small target training set. In the model, some transformation algorithms, including linear regression, Gaussian Mixture Model (GMM) and Classification and Regression Tree (CART) are involved. Experimental results show that the prosody adaptation system can generate synthesized speech which is much similar with the target speaker.

Implementation and evaluation of a Greek Text To Speech System based on an Harmonic plus Noise Model

The use of text to speech (TTS) systems beyond pure scientific applications has been gaining ground and has been incorporated in everyday life aspects. Thus, the development of TTS system, that can produce synthesized speech of high quality is more than necessary in state-of-the-art everyday life applications. This paper evaluates the performance of a TTS using harmonic plus noise model (HNM) - a speech analysis/synthesis algorithm, as part of its DSP module. A TTS for the Greek language is studied with respect to its DSP module and an evaluation is presented of the HNM algorithm in terms of overall performance and the impact of its attributes on the results quality.

SPEAKER (GOVOREC): A Complete Slovenian Text-to Speech System

While text-to-speech (TTS) systems for major world languages are quite advanced, smaller languages, like our Slovenian language, lack quality TTS synthesis. At the “Jožef Stefan” Institute a system called SPEAKER (GOVOREC) has been developed. It is capable of automatic conversion of any Slovenian text into speech. The different phases of the synthesis task are performed by several sequentially operating independent modules: text analysis, prosody generation and segmental concatenation. The first module is comprised of text normalization and grapheme-to-phoneme conversion tasks. In order to generate rules for our synthesis scheme, data were collected by analysing the readings of ten speakers, five males and five females. A two-level approach has been used for duration modeling, and a so-called superpositional approach for pitch modeling. A speech waveform is synthesized using unit selection-based methods and a concatenative TD-PSOLA or HNM+ technique. The system was first implemented in the EMA employment agent, which provides information about available jobs in Slovenia and is now used by members of the Slovenian Foundation for the Blind and Vision-Impaired. Then, it was given free of charge to all people with disabilities. The system was awarded with the first prize for innovation in the field of life improvements for people with disabilities (given by the Government Office for the Disabled and Chronically Sick of the Republic of Slovenia). SPEAKER is freely accessible for non-commercial purposes through the Internet. Currently, several leading Slovenian telecommunication companies are testing the system for providing information (e-mail, short messaging service—SMS, weather reports, traffic information) through mobile phones.

Automatic Translation of Spanish Text to Phonetics: Using Letter-to-Sound Rules

In order for non-vocal individuals to be able to communicate in a world that is oriented toward oral communication, several speech synthesis devices, such as the TI Speech Board and DecTalk, have been developed. People like Steven Hawking, a well-known physicist afflicted with Amyotrophic Lateral Sclerosis (ALS), use a speech producing device in order to overcome their vocal limitations. However, many of these synthesizers do not produce high-quality, natural sounding speech; nor do they reflect important considerations such as language-specific dialectical differences or speech variations depending on the gender and age of the intended user. Many new technologies are providing more convenient ways for non-vocal persons to interact within a predominately vocal society, and among these new technologies are multi-lingual speech synthesis devices. As the Spanish-speaking population in the United States continues to increase, so does the need for such speech synthesizers. The purpose of this article is to provide an explanation of a Spanish text-to-speech algorithm, which currently runs on an IBM compatible personal computer and is used in conjunction with speech synthesis devices to produce speech output. It represents the combined efforts of a team of colleagues at the Speech Synthesis Laboratory of the Applied Science and Enginerring Laboratories (ASEL) at the A.I. duPont Institute. 89). These methods do not address the fact that there are phonemes in the Spanish language that do not appear in English and vice versa. For example, the trilled vibrant /rrl in Spanish is not a phoneme in the English language, and the aspirated/h/l in English does not appear in Spanish. In addition, these methods are unsatisfactory because they do not capture natural speech qualities of the foreign language. The Spanish speech produced would sound veryAmericanized and would therefore be very difficult to comprehend. An alternative method involves using letter-to-sound rules developed specifically for the Spanish language in conjunction with a library of Spanish sounds to create high quality, highly intelligible Spanish speech. The first step in producing a Spanish text-tospeech system is to create an inventory of Spanish diphones, which are phonemic translations of letters. A diphone library contains at most n2 n entries, where n is the number of phonemes. The Spanish language consists of approximately 28 phonemes which implies a diphone library of 756 units. Let a 2-permutation represent a diphone. A 2-permutation is a coupled, ordered arrangement of all the phonemes (not including repetitions) of a set of Spanish phonemes, S, such as ab, ba, ac, ca, etc. Calculate the number of 2permutations of S using the following formula (Johnsonbaugh 51):