Specialist Task Force 326: Generic spoken command vocabulary for ICT devices and services (official EU and EFTA languages)

Who we are:

Team Leader: Michael Tate
Team Members: Rosemary Orr      
Helge Hüttenrauch        
Martin Boecker
Françoise Petersen

What we do :

This EC/EFTA funded Specialist Task Force (STF 326) will produce the following ETSI Standard:

• Draft ETSI ES 202 076: Human Factors (HF); User Interfaces; Generic spoken command vocabulary for ICT devices and services

Your input to and comments on our draft are welcome!

The new ETSI Standard will specify a minimum set of spoken commands required to control the generic and most common functions of ICT devices and services that use speech recognition,. These functions include command, control and editing and will be applicable to the functions required for navigation, information retrieval, basic call handling and configuration of preferences. The ETSI Standard will also cover the most common telecommunication services but it will not address user interface and dialogue design issues, speech applications, the full range of supplementary telecommunications services, performance related issues or speech output.

This new ETSI Standard will replace the previous one , covering only five languages. Considering the expansion of the EU, a revision of the Standard is necessary and includes 30 languages covering:

• Official EU languages (members and candidates)

• Official EFTA languages

• Russian

The aim is to simplify the use of the spoken interface by choosing command words that users would use spontaneously say in various situations. The project uses therefore a method which consists of the following steps:

1. Conduct interviews in order to collect a set of potential words by presenting various scenarios and ask the users which word they would in the described situation. Interviews will take place with a great number of native speakers covering the 30 languages and representing a wide range of user categories.

2. Analyse the set of collected words and analyse the frequencies of the words suggested by the interviewees.

3. Test of acoustic discrimination is necessary to avoid the choice of words that are too similar, leading to a risk that users would be misunderstood by the systems.

The STF will review the specified set of 70 common commands used in the first standard and may also include additional commands.

Read our Terms of Reference

Why we do it:

Speech recognition is a technology enabling the most natural user interaction. In recent years, speech recognition has become commercially available and viable in off-the-shelf products and services.

In order to simplify the user's learning procedure and enable reuse of knowledge between different applications and devices, it is highly desirable to standardize the most common and generic navigation, command and editing vocabularies. All users could benefit from these spoken commands, in particular those who are in a “busy hands situation” (e.g. driving a car, or working with the hands) and the disabled (e.g. the visually impaired or blind).

The availability of a spoken command vocabulary in all European languages is considered necessary, in order to cover user needs in the enlarged EU, with regard to its cultural diversity. This benefits not only the consumer but also the society and its cultural diversity, taking another step towards the achievement of the goals set by the European Commission in the eEurope 2005 Action Plan.

Currently, the ETSI Standard 202 076 specifies user tested spoken commands only for the five languages with the largest number of native speakers in the European Union (English, French, German, Italian and Spanish, as spoken in their respective countries).

Considering the expansion of the EU, a revision of the ETSI Standard has been initiated by this project, in order to provide similar support for all official European languages (including near-term enlargement candidate countries and the official languages of the EFTA countries and Russian).

How to contact us:

You are welcome to contact us at: SpokenCommands@etsi.org 

Events:

Future Events 2007

Milestone B will be presented at the HF#44 meeting on the 24-28 September 2007 at ETSI

Past Events

User Experience Conference and Interoperability Event on the 24-26 April 2007 at ETSI.

Interspeech 2007 – Eurospeech, August 27-31 in Antwerp, Belgium, see http://www.interspeech2007.org/

Milestone A approved at the HF#43 meeting on the 11-15 June at ETSI.

Time plan for the work:

Note: this information is based upon STF working assumptions.
The views expressed do not necessarily represent the position of ETSI in this context.