Spoken dialog systems for children
نویسندگان
چکیده
In this paper, we outline the main issues when designing interactive multimedia systems for children and propose a uni ed approach -acoustic, linguistic, and dialog modelingto system development. Acoustic, linguistic and dialog data collected in a Wizard of Oz experiment from 160 children ages 8-14 playing an interactive computer game are analyzed and children-speci c modeling issues are presented. Age-dependent and modality-dependent dialog ow patterns are identi ed. Furthermore, extraneous speech patterns, linguistic variability and dis uencies are investigated in spontaneous children's speech, and important new results are reported. Finally, baseline automatic speech recognition (ASR) results are presented for various tasks using simple acoustic and language models.
منابع مشابه
Dialog Studio: An Example Based Spoken Dialog System Development Workbench
In recent years, spoken dialog systems have been exploited by many researchers, but it is still too early to apply it for practical use in commercial fields. In addition to the inaccuracy of each component of dialog systems including automatic speech recognizer (ASR), spoken language understanding (SLU), and dialog management (DM), the inconvenience and the high cost of maintaining and upgradin...
متن کاملBridging Gaps for Spoken Dialog System Frameworks in Instructional Settings
Spoken dialog systems frameworks fill a crucial role in the spoken dialog systems community by providing resources to lower barriers to entry. However, different user groups have different requirements and expectations for such systems. Here, we consider the particular needs for spoken dialog systems toolkits within an instructional setting. We discuss the challenges for existing systems in mee...
متن کاملDesign and Evaluation of Spoken Dialog Systems
Interactive spoken dialog systems extend the range of automated telecommunication services beyond simple limited-choice form-filling applications to goal-directed tasks covering richer, more complex domains. Creating effective and efficient dialog systems requires not only accurate ancl robust speech recognition and language modeling, but also iterative, principled design of the user interface ...
متن کاملSemi-automatic Creation of Resources for Spoken Dialog Systems
The increasing number of spoken dialog systems calls for efficient approaches for their development and testing. Our goal is the minimization of hand-crafted resources to maximize the portability of this evaluation environment across spoken dialog systems and domains. In this paper we discuss the user simulation technique which allows us to learn general user strategies from a new corpus. We pr...
متن کاملSpeechEval – Evaluating Spoken Dialog Systems by User Simulation
In this paper, we introduce the SpeechEval system, a platform for the automatic evaluation of spoken dialog systems on the basis of learned user strategies. The increasing number of spoken dialog systems calls for efficient approaches for their development and testing. The goal of SpeechEval is the minimization of hand-crafted resources to maximize the portability of this evaluation environment...
متن کامل