December 29, 2009
Loquendo Announces Successful Conclusion of LUNA Project
By Anshu Shrivastava, TMCnet Contributor
Speech technologies provider, Loquendo, has announced that the three-year LUNA project - a European Union sponsored initiative - has concluded successfully.
According to officials with Loquendo (News - Alert), the LUNA project addressed the problem of understanding spontaneous speech in the context of automated telephone systems.
The main aim of the project was to develop a technology capable of understanding customer’s spoken requests, enabling the implementation of advanced vocal services as well as allowing callers to interact in a natural and intuitive way via spoken language understanding or “SLU.”
For SLU, the three tier software architecture was used. The tiers implement processes such as generation of semantic concept tags, semantic composition and context-sensitive validation.
Additionally, the project aimed to propose new methods, algorithms and tools to solve complex tasks and adapt to the context in which the dialog is taking place, said company officials.
“In the LUNA project we have accomplished three important results. We have designed machine learning algorithms and set the state-of-the-art for robust spoken language understanding for multiple languages and different complexity applications,” said Giuseppe Riccardi, professor and head of the adaptive multimodal information and interface lab at the University of Trento
“Our industry and public administration partners have also gained insights in such technology and evaluated LUNA dialog system prototypes that we hope to see in the speech market soon,” Riccardi said.
The project used real data collected in human to human and human to machine complex dialogues in three languages, and the results were validated with prototypes applied to different tasks. These tasks include a tourism application in French; a help desk service in Italian; and a route planner for city public transport in Polish.
In addition to offering advantages for the evolution of human-machine interaction in automated call centers, the technology also allows an increase in the automation rate of telephone services. This ensures a better distribution of the work load between operator and machine, and less waiting time for callers.
Silvia Mosso, coordinator for LUNA project at Loquendo, said that the company has “successfully” managed a complex and challenging project, working with leading research institutes and industrial partners in Europe.
In the near future, “we will see an ever-increasing pervasiveness of speech interfaces, which will become widespread, not just in call center applications, but for accessing any information by voice,” Mosso said.
Anshu Shrivastava is a contributing editor for TMCnet. To read more of Anshu’s articles, please visit her columnist page.