Previous / Next / Index

Synthetic speech may be used in several applications. Communication aids have developed from low quality talking calculators to modern 3D applications, such as talking heads. The implementation method depends mostly on used application. In some cases, such as announcement or warning systems, unrestricted vocabulary is not necessary and the best result is usually achieved with some simple messaging system. With suitable implementation some funds may also be saved. On the other hand, some applications, such as reading machines for the blind or electronic-mail readers, require unlimited vocabulary and a TTS system is needed.

The application field of synthetic speech is expanding fast whilst the quality of TTS systems is also increasing steadily. Speech synthesis systems are also becoming more affordable for common customers, which makes these systems more suitable for everyday use. For example, better availability of TTS systems may increase employing possibilities for people with communication difficulties.

Probably the most important and useful application field in speech synthesis is the reading and communication aids for the blind. Before synthesized speech, specific audio books were used where the content of the book was read into audio tape. It is clear that making such spoken copy of any large book takes several months and is very expensive. It is also easier to get information from computer with speech instead of using special bliss symbol keyboard, which is an interface for reading the Braille characters.

The first commercial TTS application was probably the Kurzweil reading machine for the blind introduced by Raymond Kurzweil in the late 1970's. It consisted of an optical scanner and text recognition software and was capable to produce quite intelligible speech from written multifont text (Klatt 1987). The prices of the first reading machines were far too high for average user and these machines were used mostly in libraries or related places. Today, the quality of reading machines has reached acceptable level and prices have become affordable for single individual, so a speech synthesizer will be very helpful and common device among visually impaired people in the future. Current systems are mostly software based, so with scanner and OCR system, it is easy to construct a reading machine for any computer environment with tolerable expenses. Regardless of how fast the development of reading and communication aids is, there is always some improvements to do.

 The most crucial factor with reading machines is speech intelligibility which should be maintained with speaking rates ranging from less than half to at least three times normal rate (Portele et al. 1996). Naturalness is also an important feature and makes the synthetic speech more acceptable. Although the naturalness is one of the most important features, it may sometimes be desirable that the listener is able to identify that speech is coming from machine (Hess 1992), so the synthetic speech should sound natural but somehow "neutral".

When the output from a speech synthesizer is listened for the first time, it may sound intelligible and pleasant. However, during longer listening period, single clicks or other weak points in the system may arise very annoying. This is called an annoying effect and it is difficult to perceive with any short-term evaluation method, so for these kind of cases, the feedback from long-term users is sometimes very essential.

Speech synthesis is currently used to read www-pages or other forms of media with normal personal computer. Information services may also be implemented through a normal telephone interface with keypad-control similar to text-tv. With modern computers it is also possible to add new features into reading aids. It is possible to implement software to read standard check forms or find the information how the newspaper article is constructed. However, sometimes it may be impossible to find correct construction of the newspaper article if it is for example divided in several pages or has an anomalous structure.

A blind person can not also see the length of an input text when starting to listen it with a speech synthesizer, so an important feature is to give in advance some information of the text to be read. For example, the synthesizer may check the document and calculate the estimated duration of reading and speak it to the listener. Also the information of bold or underlined text may be given by for example with slight change of intonation or loudness.

People who are born-deaf can not learn to speak properly and people with hearing difficulties have usually speaking difficulties. Synthesized speech gives the deafened and vocally handicapped an opportunity to communicate with people who do not understand the sign language. With a talking head it is possible to improve the quality of the communication situation even more because the visual information is the most important with the deaf and dumb. A speech synthesis system may also be used with communication over the telephone line (Klatt 1987).

Adjustable voice characteristics are very important in order to achieve individual sounding voice. Users of talking aids may also be very frustrated by an inability to convey emotions, such as happiness, sadness, urgency, or friendliness by voice. Some tools, such as HAMLET (Helpful Automatic Machine for Language and Emotional Talk) have been developed to help users to express their feelings (Murray et al. 1991, Abedjieva et al. 1993). The HAMLET system is designed to operate on a PC with high quality speech synthesizer, such as DECtalk.

With keyboard it is usually much slower to communicate than with normal speech. One way to speed up this is to use the predictive input system that always displays the most frequent word for any typed word fragment, and the user can then hit a special key to accept the prediction. Even individual pre-composed phrases, such as greetings or salutes, may be used.

Synthesized speech can be used also in many educational situations. A computer with speech synthesizer can teach 24 hours a day and 365 days a year. It can be programmed for special tasks like spelling and pronunciation teaching for different languages. It can also be used with interactive educational applications.

Especially with people who are impaired to read (dyslexics), speech synthesis may be very helpful because especially some children may feel themselves very embarrassing when they have to be helped by a teacher (Klatt 1987). It is also almost impossible to learn write and read without spoken help. With proper computer software, unsupervised training for these problems is easy and inexpensive to arrange.

A speech synthesizer connected with word processor is also a helpful aid to proof reading. Many users find it easier to detect grammatical and stylistic problems when listening than reading. Normal misspellings are also easier to detect.

The newest applications in speech synthesis are in the area of multimedia. Synthesized speech has been used for decades in all kind of telephone enquiry systems, but the quality has been far from good for common customers. Today, the quality has reached the level that normal customers are adopting it for everyday use.

Electronic mail has become very usual in last few years. However, it is sometimes impossible to read those E-mail messages when being for example abroad. There may be no proper computer available or some security problems exists. With synthetic speech e-mail messages may be listened to via normal telephone line. Synthesized speech may also be used to speak out short text messages (sms) in mobile phones.

For totally interactive multimedia applications an automatic speech recognition system is also needed. The automatic recognition of fluent speech is still far away, but the quality of current systems is at least so good that it can be used to give some control commands, such as yes/no, on/off, or ok/cancel.

In principle, speech synthesis may be used in all kind of human-machine interactions. For example, in warning and alarm systems synthesized speech may be used to give more accurate information of the current situation. Using speech instead of warning lights or buzzers gives an opportunity to reach the warning signal for example from a different room. Speech synthesizer may also be used to receive some desktop messages from a computer, such as printer activity or received e-mail.

In the future, if speech recognition techniques reach adequate level, synthesized speech may also be used in language interpreters or several other communication systems, such as videophones, videoconferencing, or talking mobile phones. If it is possible to recognize speech, transcribe it into ASCII string, and then resynthesize it back to speech, a large amount of transmission capacity may be saved. With talking mobile phones it is possible to increase the usability considerably for example with visually impaired users or in situations where it is difficult or even dangerous to try to reach the visual information. It is obvious that it is less dangerous to listen than to read the output from mobile phone for example when driving a car.

During last few decades the communication aids have been developed from talking calculators to modern three-dimensional audiovisual applications. The application field for speech synthesis is becoming wider all the time which brings also more funds into research and development areas. Speech synthesis has also several application frameworks which are described in the following chapter.

Previous / Next / Index