This paper describes the first participation of MARY TTS HMM-based voices in a Blizzard challenge. An architecture for synthesis of expressive speech based on the MARY TTS system and sentiment analysis of text is proposed. The creation of several HMM-based voices in different styles using audiobook data is described. Preliminary results on perception of different voice styles and the appropriat...

Text preprocessing plays an important role in a textto-speech (TTS) synthesis system. The correct detection and interpretation of input strings influence the overall system accuracy and contribute to the conversion of an unrestricted text into synthetic speech. This paper describes the design philosophy of a preprocessing module for a TTS system in Romanian language. The preprocessor is impleme...

Every person in the world want to share their information, thoughts from one person to another. So communication plays very important role into that. Speech is the primary means of communication. Hindi is very popular and well known language of India. Everybody understands and speak and write easily. Our System developed for Hindi Text to Speech and Speech to Text Conversion mainly into the Hin...

Open Access Recently, as the numbers of diagnostic endoscopic procedures and therapeutic procedures such as endoscopic mu-cosal resection (EMR), endoscopic submucosal dissection (ESD), and full-thickness resection of subepithelial tumors are increasing, the incidence of iatrogenic perforations is also increasing. The use of natural orifice transluminal endoscopic surgery (NOTES) techniques also...

The existence of sequences in the human genome which can be a target for triplex formation, and accordingly are candidates for anti-gene therapies, has been studied by using bioinformatics tools. It was found that the population of triplex-forming oligonucleotide target sequences (TTS) is much more abundant than that expected from simple random models. The population of TTS is large in all the ...

Feed-forward deep neural networks (DNNs) based text-tospeech (TTS) synthesis, which employs a multi-layered structure to exploit the statistical correlations between rich contextual information and the corresponding acoustic features, has been shown to outperform a decision tree based, GMM-HMM counterpart. However, the DNN-based TTS training has not taken the whole sequence, i.e., sentence, int...

Text to speech (TTS) is synthetic, generated speech. Typed text is converted into speech using various approaches. This project work is about building a Text to Speech converter using a VLSI (Very Large Scale Integration) approach. TTS conversion has numerous applications from enabling Robots to speak, to reading out to the blind. Specialized applications require innovative approaches for effic...

This paper explores the use of micro-prosody in improving the quality of synthesised speech in concatenated text to speech synthesis (TTS) systems. Micro-prosody are defined as prosodic signals within context-dependent triphone units and across neighbouring triphones. Micro-prosody parameters are modelled using a Markovian model whose state distributions depend on the current linguistic-prosodi...

This paper describes a novel text-to-speech (TTS) technique based on deep convolutional neural networks (CNN), without any recurrent units. Recurrent neural network (RNN) has been a standard technique to model sequential data recently, and this technique has been used in some cutting-edge neural TTS techniques. However, training RNN component often requires a very powerful computer, or very lon...

Most Text to Speech (TTS) systems today assume that the input text is in a single language and is written in the same language that the text needs to be synthesized in. However, in bilingual and multilingual communities, code mixing or code switching occurs in speech, in which speakers switch between languages in the same utterance. Due to the popularity of social media, we now see code-mixing ...