The key strategy in the Banana Information Line was the use of its automated TTS system that allows users to access the information in either Kiswahili or English. According to the organisers, because anyone with a land line or mobile phone could access the information line, communities that were more difficult to reach by traditional means could more easily access the agricultural information they needed to more efficiently grow their crops. A TTS line bypasses the need for literacy, as well as the problem of reaching farmers living in very remote areas. Farmers are able to call the line any time of day, every day, thereby allowing them to get information when they need it, and when it is most convenient for them.

TTS systems read out text that was input by the project organisers on the project website, in a natural-sounding human voice. LLSTI says that this made the Banana Information Line easy to update because all they had to do is edit the web pages from which the system got its text. The system was, in this way, fairly simple and cost-effective to maintain. The speech was generated through sounds pulled from carefully selected pre-recorded sentences that had nothing to do with the information line itself, but that allowed the system to form any word in a natural imitation of a human voice.

In general terms, developing a TTS system involves the following steps:

• Defining the language characteristics: phone-set (i.e. the sounds used in the language), letter-to-sound rules, the rules of syllabification (the separation of words into syllables), etc.
• Selecting a set of phonetically balanced sentences, from a large database of phonetically transcribed texts that cover all the different phonetic combinations of the language in as few sentences as possible.
• Selecting a speaker. The choice of voice is the single most important decision in the development of a TTS system. This may appear to be counter-intuitive – after all, doesn’t almost everyone speak clearly enough to be understood? But TTS requires a clear, precise rendition of every word in the database. The system constructs its output by combining small segments of words in the database, so each one has to be exactly right. In addition, the speech needs to be as intelligible as possible to start with, so that any deterioration in quality that may occur in the process of joining up these segments has the least possible impact.
• Recording the phonetically balanced sentences. For Kiswahili, there were about 400 sentences, which took around 45 minutes to record; for most other languages more spoken sentences are needed.
• Making phonetic annotations of the recordings by hand. Although this can be done automatically, any resulting errors can create problems for the TTS output.
• Compiling all the data into a TTS system using Festival, an open source software package developed at the University of Edinburgh.
• Testing the system.

   

Agriculture, New Technologies.

The Banana Information Line was formally evaluated with the help of a carefully selected group of 10 farmers in Kirinyaga district. According to the organisers, the evaluation revealed that seven out of the ten participants chose to listen to the information in English, but then struggled with the British accent. Those who chose Kiswahili loved the voice, but then struggled with the formal Kiswahili grammar used in the translation. LLSTI noted that all the farmers said that they liked the voice system and that they preferred it to written material, but it was clear that the accent and translation issues would need to be fixed before it could be put to wider use. The organisers found that the farmers liked a Kenyan English TTS that was still under development better than the original two languages. This TTS has now been completed, and, along with an improved Kiswahili TTS, is being used in the recently-launched (April 2008) NAFIS Information Line, which brings the pilot project structure to a larger scale with more crops and livestock.

The LLSTI says that with the introduction of mobile data services across Africa, a future version of the information line becomes possible where the TTS system runs on the phone itself. Only the text data would be transferred, which the phone would then convert to speech. The organisers say this could be an attractive option for a number of reasons. First, the cost of using the information line is much lower – mobile calls are still quite expensive in Kenya. Second, users can access the information they need using visual (pictorial or icon) menus, with a text search function for those who are happy to try it. Third, pictures and key numbers/words can be displayed along with the voice, making it easier for users to absorb the information and remember it afterwards.

During the evaluation of the Banana Information Line, the project team consulted with NALEP to build up a picture of the many services a voice information portal could offer farmers in the future:

• separate phone lines for different crops;
• an online database where anyone, such as district or provincial level extension workers, can update data or add new information to the system, and where farmers can add their own information or post questions;
• an alert service for farmers, offering up-to-date commodity prices and other market information, weather reports, and urgent announcements of disease outbreaks, e.g. bird flu;
• local information, such as which crops are most suitable for a specific area, and contact information for agricultural extension officers;
• personalised information services;
• a unique caller ID or PIN code for each farmer so that they would not have to re-enter information; and
• a voice system that allows farmers to choose to receive information by SMS or email.

LLSTI began in 2003 as a global initiative led by Outside Echo, a United Kingdom not-for-profit organisation which facilitates audio access to information, and works together with partners from India, South Africa, Kenya, and Nigeria. LLSTI provides the support needed for a team which has no prior knowledge of speech technology to produce usable, natural-sounding voices with a TTS system. The main requirements are a linguist, a software engineer, and a motivated team leader who preferably is an engineer as well. Each team is normally based in the area where the language is spoken, and part of a university or research institute.