Voice Application Development for Android: A practical guide to develop advanced and exciting voice applications for Android using open source software

Text-to-speech synthesis, often abbreviated to TTS, is a technology that enables a written text to be converted into speech. TTS has been used widely to provide screen reading for people with visual impairments, and also for users with severe speech impairments. Perhaps the best known user of speech synthesis technology is the physicist Stephen Hawking who suffers from motor neurone disease and uses TTS as his speech has become unintelligible. With the aid of word prediction technology he is able to construct a sentence which he then sends to the built-in TTS system (see further: http://www.hawking.org.uk/the-computer.html).

TTS is also used widely in situations where the user's hands or eyes are busy, for example, while driving navigation systems speak the directions as the vehicle progresses along a route. Another widespread use for TTS is in public announcement systems, for example, at airports or train stations. TTS is also used in phone-based call...

There are two main stages in text-to-speech synthesis:

There can be many problems in the text analysis stage. For example, what is the correct pronunciation of the word staring? Is it to be based on the combination of the word star + ing or of stare + ing? Determining the answer to this question involves complex analysis of the structure of words; in this case, determining how the root form of a word such as stare is changed by the addition of a suffix such as ing.

There are also words that have alternative pronunciations depending on their use in a particular sentence. For example, live as a verb will rhyme with give, but as an adjective it rhymes with five. The part of speech also affects stress assignment within a word; for example, record as a noun is pronounced 'record (with the stress...

Although the quality of TTS has improved considerably over the past few years, many commercial enterprises prefer to use pre-recorded speech in order to guarantee high-quality output. Professional artists, often referred to as voice talent, are employed to record the system's prompts.

The downside of pre-recorded prompts is that they cannot be used where the text to be output is unpredictable—as in apps for reading e-mail, text messages, or news, or in applications where new names are being continually added to the customer list. Even where the text can be predicted but involves a large number of combinations—as in flight announcements at airports—the different elements of the output have to be concatenated from pre-recorded segments but in many cases the result is jerky and unnatural. Another situation is where output in other languages might be made available. It would be possible to employ voice talent to record the output in the various languages...

TTS has been available on Android devices since Android 1.6 (API Level 4).The components of the Google TTS API (package android.speech.tts) are documented at http://developer.android.com/reference/android/speech/tts/package-summary.html. Interfaces and classes are listed and further details can be obtained by clicking on these.

TextToSpeech tts = new TextToSpeech(this, new OnInitListener(){ 
    public void onInit(int status){ 
        if (status == TextToSpeech.SUCCESS) 
              speak("Hello...

In order to avoid repeating the code in several places, and to be able to focus on the new parts as we progress to more complex applications, we have encapsulated the most frequently used TTS functionalities into a library named TTSLib (see sandra.libs.tts in the source code), which is employed in the different applications.

The TTS.java class has been created following the Singleton design pattern. This means that there can only be a single instance of this class, and thus an app that employs the library uses a single TTS object with which all messages are synthesized. This has multiple advantages, such as optimizing resources and preventing developers from unwittingly creating multiple TextToSpeech instances within the same application.

This chapter has shown how to use the Google TTS API to implement text to speech synthesis on a device. An overview of the technology behind text to speech synthesis was provided, followed by an introduction to the elements of the Google TTS API. Two examples were presented illustrating the basics of text-to-speech synthesis. In subsequent chapters more sophisticated approaches will be developed.

The next chapter deals with the other side of the speech coin: speech-to-text (or speech recognition).