Integrating Incremental Speech Recognition and POMDP-Based Dialogue Systems
نویسندگان
چکیده
The goal of this paper is to present a first step toward integrating Incremental Speech Recognition (ISR) and Partially-Observable Markov Decision Process (POMDP) based dialogue systems. The former provides support for advanced turn-taking behavior while the other increases the semantic accuracy of speech recognition results. We present an Incremental Interaction Manager that supports the use of ISR with strictly turn-based dialogue managers. We then show that using a POMDP-based dialogue manager with ISR substantially improves the semantic accuracy of incremental results.
منابع مشابه
Effects of user modeling on POMDP-based dialogue systems
Partially observable Markov decision processes (POMDPs) have gained significant interest in research on spoken dialogue systems, due to among many benefits its ability to naturally model the dialogue strategy selection problem under the unreliability in automated speech recognition. However, the POMDP approaches are essentially model-based, and as a result, the dialogue strategy computed from P...
متن کاملSpoken Dialogue Management Using Probabilistic Reasoning
Spoken dialogue managers have benefited from stochastic planners such as MDPs. However, so far, MDPs do not handle well noisy and ambiguous speech utterances. We use a POMDP-style approach to generate dialogue strategies by inverting the notion of dialogue state; the state represents the user's intentions, rather than the system state. We compare the performance of MDP and POMDP dialogue manage...
متن کاملProbabilistic Dialogue Modeling for Speech-Enabled Assistive Technology
People with motor disabilities often face substantial challenges using interfaces designed for manual interaction. Although such obstacles might be partially alleviated by automatic speech recognition, these individuals may also have cooccurring speech-language challenges that result in high recognition error rates. In this paper, we investigate how augmenting speech applications with dialogue ...
متن کاملIntegrating prosodic modelling with incremental speech recognition
We describe ongoing and proposed work concerning incremental prosody extraction and classification for a spoken dialogue system. The system described will be tightly integrated with the SDS’s speech recogntion which also works incrementally. The proposed architecture should allow for more control over the user interaction experience, for example allowing more precise and timely end-ofutterance ...
متن کاملSpoken Dialogue Management Using Probabilistic Reasoning
Spoken dialogue managers have benefited from using stochastic planners such as Markov Decision Processes (MDPs). However, so far, MDPs do not handle well noisy and ambiguous speech utterances. We use a Partially Observable Markov Decision Process (POMDP)-style approach to generate dialogue strategies by inverting the notion of dialogue state; the state represents the user’s intentions, rather t...
متن کامل