Talking to Machines: Introducing Robot Perception to Resolve Speech Recognition Uncertainties

Abstract

The use of spontaneous speech as a form of communication between humans and robots is a potential solution for more efficient human-robot interactions. Accuracy is one of the main problems associated with the automatic speech recognition (ASR) component of human-robot interactive systems. The standard ASR approach is based on statistical methods applied to phoneme domains. However, some problems cannot be solved with the rule-based approaches used so far; therefore, alternative strategies could be the solution. The aim of this paper is to investigate some aspects related to the use of a robot's perceptive abilities to increase the robustness of ASR components. The robot evaluative abilities are used to incrementally build knowledge that will be used during the recognition phase. This paper covers aspects concerning the use of time-warping algorithms to improve the speech recognition performance. In particular, aspects related to the accuracy and efficiency of this approach when applied to whole-sentence speech signals are discussed.

A prototype for a conversational companion for reminiscing about images

“…By combining the semantic content and acoustic information of the current utterance the uncertainty of the current emotional state can be reduced (Lauria, 2007;Lee et al, 2002) Having established this understanding the Companion will have a number of tools with which to manipulate the situation.…”

Some background on dialogue management and conversational speech for dialogue systems

“…2000) All of these factors present a challenge when training conversational systems, but the recursive nature of dialogue also allows us to exploit a number of beneficial aspects. As highlighted by (Thorisson,1997) we should "keep in mind that the agent can always ask the user a question when the data doesn't make "sense"' and in the context of artificial dialogues an utterance doesn't make sense if it cannot be grounded in the systems dialogue manager (Lauria, 2007). The system only needs to resolve uncertainty to the point where it is able to act and reply in a meaningful fashion.…”