Speech Technology - June 2008 - (Page 6) PATTI PRICE, BILL SCHOLZ, AND MATT YUSCHIK VIEW FROM AVIOS A Look at AVIOS’ Speech and Multimodality Contest Students introduce voice to apps covering everything from airplanes to arithmetic he Applied Voice Input-Output Society (AVIOS) temperature, length, and weight. It provided a solid use of announced the winners of its second annual Speech speech recognition and text-to-speech. Application Student Contest at the recent Voice Search Two additional prizes were awarded for compelling appliConference in San Diego. This year’s 19 submissions pro- cations that were outstanding in one or more, but not all, of vided voice-only applications on a BeVocal host and multi- the evaluation criteria. One of them was a GPS-based direcmodal applications using X+V, VoiceXML, or SALT tory assistance application that ran on the Windows Mobile scripting languages running on Internet Explorer 6, Opera, platform. It supported a navigation tool that accepted a spoVoxeo/Skype, Firefox, or Windows Mobile 5 browsers. The ken city name and brought up the corresponding Google map resulting applications represented the collective works of 37 and allowed for voice commands to change the map scale and students and eight faculty advisers at nine institutions in compass direction. The other was a Visual Flight Rules comfour countries. munication tutorial that provided textual training material Applications were evaluated by five speech technology with a graphic aircraft control panel, then proposed typical leaders from Microsoft, Nuance, Convergys, and Fonix on communication tasks that a student-pilot would say to an airthe basis of technical superiority, innovation, user friend- port flight controller. Training feedback included displaying liness, and usefulness. Winners received software pack- and saying the correct communication statement, and having ages, popular hardware, or remunerative the student try the task again. The goal is to awards, such as airfare and lodging for have the student successfully complete the A beneficial side the next Voice Search Conference, from simulated dialogue with the flight coneffect of the contest corporate sponsors Google, Microsoft, troller. Other student projects included a was helping students learn more about the Samsung, and Voice Objects. Student voice-controlled dictionary interface, a mulcorporate sponsors, resumes were made available to the spontimodal voting application, an adventure while helping the soring corporations. game framework, and a step-by-step tutorial corporate sponsors The winning application in the voicefor repotting an orchid. To access and samfind emerging talent. only category involved five children’s educaple the applications, visit our Web site at tional games about counting, adding, www.avios.org/contest/. feelings, days of the week, and seasons of the year. This clevAVIOS’ goals in sponsoring the contest were to foster creative erly designed voice interface, which made good use of barge- thinking in the use of speech technology and to encourage stuin, offered appropriate prompts to cue a child to the task and dent participation in AVIOS. A beneficial side effect of the conto appropriately narrow the task to enable good performance test was helping students learn more about the corporate with children’s voices. The runner up’s application accepted sponsors, while helping the corporate sponsors find emerging voice input of common fast-food items and provided a calorie talent. Comments from participating students indicate that the count of the selected lunch meal. Again, clever use of the contest was a success: “The contest was a great chance for me prompts appropriately narrowed the task for the speech to gain some in-depth knowledge.” “I was very satisfied with recognition system. learning to write voice applications.” “There is a notable differThe winning application in the multimodal category was ence between theory and practice in speech recognition.” a speech therapy game in which the player (a child) spoke And (from a sponsor) “Wow! I want to contact that student!” the name of different items in a path that led to a picture Planning for next year’s contest is already under way. of a cake, the reward. Speaking the name of each item pro- Visit our Web site for details or to let us know your suggesvided practice of phonemes (e.g., /l/, /k/) that are typically tions for improvements. difficult for children to produce. Numerous encouraging Patti Price has more than 20 years of experience in developing and transferring retry prompts and error-handling actions helped the child speech and language technology. She also cofounded Nuance, BravoBrava!, and Soliloquy Learning. Bill Scholz, Ph.D., is a speech technology consultant with reach the goal while learning to correctly pronounce the more than 30 years of experience in research and product development in computer-based training and expert systems. Matt Yuschik, Ph.D., is a human factors items on the path. The runner-up multimodal application specialist at Convergys. converted English units to metric units for values of T 6 | Speech Technology JUNE 2008 www.speechtechmag.com http://www.avios.org/contest/ http://www.speechtechmag.com
For optimal viewing of this digital publication, please enable JavaScript and then refresh the page. If you would like to try to load the digital publication without using Flash Player detection, please click here.