TeliSpeech

Studio

Quality of Service and speech recognition accuracy is one of the key factors to the success of a speech application.

Studio is a set of Eclipse based plugin that will help you manage the Quality of Service of a speech application, manages speech data collected on the speech platform and improve the performance of speech recognition.

The tool kit allows you to work in complete autonomy. A dedicated OnMobile team is ready help if you'd rather rely on our experience in speech service deployment to maintain a high Quality of Service

Grammars can be simultaneously developed and tested independently from the use of your voice service during the first stage of this cycle.

Using the tuning toolkit, Recognition performance via phonetic and acoustic optimization is improved during the second stage of the cycle. teliSpeech sets itself apart from its rivals: by collecting data from a live system and continuing to improve the accuracy to near perfection.

Performance analysis tool reports reliable measures and recognition rates during the entire life-cycle of a service.

Unique QoS management

To move a step further in the improvement of client satisfaction, teliSpeech integrates a complete set of tools to manage the Quality of Service. Word command orientated, it allows you to automate numerous quality control tasks in batch mode, making it easier to put them into operation. At the heart of this set up, the performance analysis tool reports reliable measures and recognition rates during the entire life-cycle of a service.

In the first stage of this cycle, you simultaneously develop and test your grammars independently from the use of your voice service.

In the second stage of the cycle, you improve recognition performance via phonetic and acoustic optimisation.

So the teliSpeech Quality of Service Management tools can be the basis of the definition of a commitment between our partners and their clients, since the tools ensure that they can master the work to achieve given performance targets.

Measure your QoS

The quality of a voice service can be measured at each stage of its life cycle :

• Development produces the source code of the grammars, the words that need to be recognised, on the basis of the dialogue specifications
• Testing validates the grammars one by one and then integrates them together outside the target platform
• Data collection is essential to define non-regression tests and obtain pertinent results during the performance optimisation stage.
• Evaluation of recognition rate must be carried out through preliminary tests until the follow up during production; this is the cornerstone of the monitoring metrics and the Quality of Service Management.
• Phonetic optimisation improves the precision of the phonetic definitions. You can create your own lexicons composed of words with particular pronunciations.
• Acoustic optimisation improves the acoustic representation of the words in a grammar on the basis of collected speech data. This is the ultimate step in optimising performance with teliSpeech.

QoS performance evaluation