Having been among the very first players to adopt the Unit Selection technique, Loquendo is now the first company to bring expressive synthetic speech to the market.

Loquendo's voices have been enriched with a repertoire of "expressive cues", which enable TTS users to enliven their voice prompts. This new development signals an important landmark in the pursuit of expressive synthetic speech.

Developing both stylistically and emotionally expressive synthetic speech has been one of Loquendo's objectives for several years; research has covered both language modelling and techniques to make the TTS software more manageable, without compromising on the natural qualities achieved through Unit Selection. In the near future, research will make it possible to synthesize any kind of text in a specific style (e.g. emphatic, formal, informal, etc.) and in the emotional tone required (e.g. happy, sad, angry, etc.).

The speech market does not currently offer solutions that are capable of changing the style and tone of a voice, upon command or according to the nature of the text itself, without compromising on acoustic quality. Loquendo, however, is now offering its customers the chance to make their vocal messages truly lifelike and expressive. Just like human conversation, expressive intention is conveyed through conventional phrases and exclamations, which are pronounced with a natural and colourful intonation. As a result, the entire message becomes far more expressive.

Example 1:
Welcome to Loquendo's TTS system. You can write anything you like, and I'll say it. Amazing! Just imagine it!  It's not so hard, is it? I can say: fantastic. But it sound much better like this: Fantastic! Congratulations. Oh, sorry! Congratulations!  I must go now. Thanks to you all!

Loquendo's repertoire of "expressive cues" contains conventional figures of speech, such as greetings and exclamations ("hello!", "oh no!", "thank you!"), interjections ("Oh!", "Well!", "Hmm!") and paralinguistic events (e.g. breathing, coughing, laughter, etc.), suggesting additional layers of expressive intent (confirmation, doubt, gratitude, etc.).

Example 2:
Here's an example. Let's imagine we're arguing. If I say: no, nonsense. That's unbelievable. No, you wouldn't believe me. But if I say it like this: No! Nonsense! That's unbelievable! Doh!  It's sound much better. What do you think? Mmm, it's more believable. Don't you think so? Cheerio!

In order to achieve the greatest degree of naturalness, the same phrase can be pronounced using different styles and intonations, from neutral to emphatic, from sad to amazed.

Example 3:
\_Throat Perfect!  I can speak almost like a human being. Fantastic. Or would you prefer to hear me say: Fantastic!  \_Laugh Now you can choose. Hello everybody, or: Hello everybody!  Thank you so much, see you tomorrow, or: Thank you so much, see you tomorrow!

Example 4: Using Emphatic expressions
Hello and welcome! My name is Simon. I'm the English Loquendo TTS voice. Now I can sound much more natural. For example, I can say: it's a pleasure. But I can also say it like this: It's a pleasure!

The 'Expressive Cues' can be typed directly into the text with the appropriate punctuation, or can be selected from an easy to use drop-down menu in which the user will find the full repertoire of "expressive cues" available for each voice. The list is structured according to intuitive linguistic categories, so that appropriate formulas can be rapidly and easily found. In this way messages, dialogue, and narratives can be easily constructed and read by Loquendo's synthetic voices in a truly expressive and natural sounding way.