Given that state of the art speech synthesis systems have already reached a high naturalness level, it is time to move to talking speech from the actual read speech framework. For this purpose it is thus necessary to investigate how disfluencies can be included in speech synthesis and even increase its naturalness. This paper builds on a previously presented work and focuses on finding a local ...

This paper presents an interactive tool for working with parametric speech synthesis. The tool facilitates editing of parameter tracks, and it provides real-time feedback of the synthesised speech. It serves as an interface to KTH’s multilingual rule based synthesis system, and can be used to control a formant synthesiser as well as a 3-D “talking head”. The tool has been used in research and e...

Can we make a difference? If I had a pound for every time I have heard someone tell us that we can make a difference I think I could personally end world poverty. I have a copy of a cartoon in which someone says, ‘What difference can one person make?’ In the next frame two or three more speech bubbles have appeared asking the same question. In the final frame there are a plethora of similar spe...

Several recent studies have shown that speech production develops in an organized way, already in the first twelve months of life. This development is determined by several factors such as anatomical growth and physiological constraints. Studying the sound production of deaf infants and comparing this with that of normally hearing infants, can give more insight into the role of auditory speech ...

This paper reports on the development of Chatako-AID, a communication aid for non-vocal people using corpus-based cocatenative speech synthesis by creating a speech corpus especially designed for such use. The concept of Chatako-AID; synthesis with the user’s voice, which makes use of precomposed texts, is highly appreciated by the target user. This confirms that the recording of a minimum set ...

In this paper we investigate the rapid deployment of a twoway Afrikaans to English Speech-to-Speech Translation system. We discuss the approaches and amount of work involved to port a system to a new language pair, i.e. the steps required to rapidly adapt ASR, MT and TTS component to Afrikaans under limited time and data constraints. The resulting system represents the first prototype built for...

Simultaneous speech translation is a technology that attempts to reduce the delay inherent in speech translation by beginning translation before the end of explicit sentence boundaries. Despite best efforts, there is still often a trade-off between speed and accuracy in these systems, with systems with less delay also achieving lower accuracy. However, somewhat surprisingly, there is no previou...

One of the most important social problems that many of the developed countries face is the constant rise of the percentage of the elderly population values. A major health issue affecting this part of the population is the appearance of dementia of the Alzheimers type (AD) which is the most common case of dementia, affecting around 50 million people worldwide. In addition, the frequency of the ...

This paper presents the validation of the expressive content of an acted oral corpus produced to be used in speech synthesis. Firstly, objective validation has been conducted by means of automatic emotion identification techniques using statistical features obtained from the prosodic parameters of speech. Secondly, a listening test has been performed with a subset of utterances. The relationshi...

This paper deals with speech communication aspects with an accent on speech dialogues, in which one communication partner is a computer. After some basic definitions, we discuss the speech components of a man-machine dialogue, namely speech recognition and speech synthesis. It will be shown that a computer is far away from human’s ability to recognise or understand speech.