A Methodology for Learning Optimal Dialog Strategies

EURASIP J. Adv. Signal Process.

López-Cózar

2011

Self Cite

In this paper we propose a method for predicting the user mental state for the development of more efficient and usable spoken dialogue systems. This prediction, carried out for each user turn in the dialogue, makes it possible to adapt the system dynamically to the user needs. The mental state is built on the basis of the emotional state of the user and their intention, and is recognized by means of a module conceived as an intermediate phase between natural language understanding and the dialogue management in the architecture of the systems. We have implemented the method in the UAH system, for which the evaluation results with both simulated and real users show that taking into account the user's mental state improves system performance as well as its perceived quality.

Section: Evaluation With a User Simulatormentioning

confidence: 99%

Predicting user mental states in spoken dialogue systems

Callejas

EURASIP J. Adv. Signal Process.

López-Cózar

2011

Self Cite

“…In this case, the system uses the multimodal NetFront Browser v4.1 5 . NetFront supports advanced mobile voice recognition technologies based on X+V, including voice synthesis and voice recognition of mobile Internet data in voice supported web pages.…”

Section: The Voiceapp Multimodal Dialog Systemmentioning

confidence: 99%

“…On the one hand, some authors have developed ad-hoc solutions focused on specific tasks, as e-commerce [3], chat functionalities [4], healthcare services [5], surveys [6], or recommendation systems [7]. On the other hand, it is possible to add a speech interface to an existing web browser [8].…”

Section: Introductionmentioning

confidence: 99%

The VoiceApp System: Speech Technologies to Access the Semantic Web

Advances in Artificial Intelligence

Molina

Corrales

2011

Self Cite

Abstract. Maximizing accessibility is not always the main objective in the design of web applications, specially if it is concerned with facilitating access for disabled people. In this paper we present the VoiceApp multimodal dialog system, which enables to access and browse Internet by means of speech. The system consists of several modules that provide different user experiences on the web. Voice Dictionary allows the multimodal access to the Wikipedia encyclopedia, Voice Pronunciations has been developed to facilitate the learning of new languages by means of games with words and images, whereas Voice Browser provides a fast and effective multimodal interface to the Google web search engine. All the applications in the system can be accessed multimodally using traditional graphic user interfaces such as keyboard and mouse, and/or by means of voice commands. Thus, the results are accessible also for motorhandicapped and visually impaired users and are easier to access by any user in small hand-held devices where graphical interfaces are in some cases difficult to employ.

“…The dialog model is learned from a labeled training corpus for the task and is mainly based on modeling sequences of the system and user dialog acts and the definition of a data structure which takes into account the data supplied by the user throughout the dialog, and makes the estimation of the model from the training data manageable. Our statistical dialog management technique has been previously applied to several tasks (including e-health [28], a fast food domain [35], or travel planning [27]) to verify its correct operation in very well-known domains related to commercial applications of dialog systems.…”

Section: Introductionmentioning

confidence: 99%

Bringing together commercial and academic perspectives for the development of intelligent AmI interfaces

Journal of Ambient Intelligence and Smart Environments

Molina

Callejas

2012

Self Cite

The users of Ambient Intelligence systems expect an intelligent behavior from their environment, receiving adapted and easily accessible services and functionality. This can only be possible if the communication between the user and the system is carried out through an interface that is simple (i.e. which does not have a steep learning curve), fluid (i.e. the communication takes place rapidly and effectively), and robust (i.e. the system understands the user correctly). Natural language interfaces such as dialog systems combine the previous three requisites, as they are based on a spoken conversation between the user and the system that resembles human communication. The current industrial development of commercial dialog systems deploys robust interfaces in strictly defined application domains. However, commercial systems have not yet adopted the new perspective proposed in the academic settings, which would allow straightforward adaptation of these interfaces to various application domains. This would be highly beneficial for their use in AmI settings as the same interface could be used in varying environments. In this paper, we propose a new approach to bridge the gap between the academic and industrial perspectives in order to develop dialog systems using an academic paradigm while employing the industrial standards, which makes it possible to obtain new generation interfaces without the need for changing the already existing commercial infrastructures. Our proposal has been evaluated with the successful development of a real dialog system that follows our proposed approach to manage dialog and generates code compliant with the industry-wide standard VoiceXML.