Text-to-Speech Technology in Training Presentations:
Eliminating an Expensive Bottleneck

Recorded Narration – the Bottleneck in PowerPoint-Based Training

US industry spends $200 billion a year on training. PowerPoint presentations are ubiquitous in a wide range of training applications, from a small-scale presentation to present an idea to a group of people up to a web-based course designed to reach thousands of people. To insure proper understanding of the material, it is frequently necessary to include an accompanying narration that explains and adds detail.

Creating a professional voice-over narration has been a challenge in the industry: it requires a professional voice talent and a recording studio. For large-scale training presentations that do use professional voice talents, the voice recording frequently becomes a bottleneck in the course production process. With courses numbering in the hundreds and the frequent deadlines for changes, updates and new courses it has been difficult to schedule recording and re-recording sessions using the same voice -- as well as expensive. The result is that in many cases the new information is not made available to the customer in a timely fashion -- and training costs are high.

Another issue is the need to synchronize the voice recording with the PowerPoint screen visuals, an activity that can take more time than the recording itself.

Text-to-Speech Technology in Presentation Software

Work on speech technology has been going on for years; it is a technologically challenging subject but progress has been made. Two years ago, Microsoft introduced their Speech Server, effectively placing speech technology in the mainstream.

Most of the emphasis has been placed on voice recognition, which might be called speech-to-text. However, the sister technology, text-to-speech (TTS), has also developed in quality to the point where it can now be used in presentation software like Microsoft PowerPoint to empower presentations with affordable, quality narration.

The new TTS technology is an affordable and convenient way to provide audio information synchronized with the presentation visuals to have the maximum effect on the viewer. It also lets the presentation designer remove written text from the screen, freeing up valuable real estate for the more powerful pictures and graphics that better illustrate the narration.

For more information about text-to-speech technology, see Text-to-Speech.

Knowledge Transfer Applications

Presentations whose purpose is to transfer knowledge are well-suited to TTS presentation technology. This type of presentation is usually given to people who have a need to receive and understand the information being presented, for example, training presentations. In this situation, as long as the information is clearly presented, the quality of the voice is not critical and TTS voices are quite acceptable.

Training Applications

PowerPoint-based training stands to benefit significantly from TTS presentation technology, for the following reasons:

· As mentioned, training presentations are well-suited to TTS presentation technology. TTS voices can pronounce even the most technical words clearly, resulting in a very effective explanation of the subject.

· Companies that need to maintain large numbers of training courses find that TTS technology lets them update their courses with the latest changes and still make the course release deadlines. One worker can update the text and regenerate the course in one session -- at any time.

· Using TTS presentation technology makes the training process more manageable by removing the human element.

Speech-Over Studio Platform

To make TTS presentation technology work in a cost-effective way, you need an efficient platform for integrating the TTS system with the presentation software. Tuval Software Industries’ Speech-Over Studio™ is such a platform for PowerPoint.

Among the features and benefits offered by Speech-Over Studio:

· Speech editor for quick and easy entry and editing of speech text, including SAPI voice modulation tags, and association of speech with screen shape. Text can be typed in or dictated.

· Integration of multiple voices in a presentation to make it more interesting and varied

· Alternative narrations of a presentation for different audiences, including in different languages.

· Automatic synchronization of narration with screen animation replaces time-consuming manual synchronization of recorded voices.

The table below shows the advantages of Speech-Over Studio over the voice-over system.

 

Conclusion

Tuval Software Industries’ Speech-Over Studio replaces the professional voice talent with professional quality text-based speech generated by state-of-the-art text-to-speech technology. Speech-Over Studio’s implementation of the TTS technology is capable of reducing the cost of producing a synchronized narration by half and lets you update courses with the latest changes and still make the course release deadlines.

Abstract

The cost and scheduling requirements of professional voice talents make recording voice-over narrations for PowerPoint presentations an expensive bottleneck in the production of training courses. This is especially true for organizations where hundreds of courses need to be updated and new ones created at an ever-increasing rate.

Tuval Software Industries’ innovative Speech-Over Studio software uses text-to-speech technology to eliminate the professional voice talent entirely and replace it with professional quality text-based speech.

Tuval Software

Easy-to-Create, Easy-to-Change Audio Presentations for Business and Education