Human-Robot interactions: an investigation on the use of robots' perceptive abilities to improve its speech recognition performance

摘要

The use of spontaneous speech as a form of communication between humans and robots is a potential solution for more efficient human robot interactions. Automatic Speech Recognition (ASR) accuracy is one of the main problems associated with this approach. The standard ASR approach is based on statistical methods applied to phoneme domains. However, some recognition problems cannot be solved with these 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 robots' perceptive abilities to increase the accuracy for automatic speech recognition components used to interact with humans The robot evaluative abilities are used to incrementally build knowledge that will be used during the recognition phase. The aspect discussed here concerns the use of a pattern-matching based component to improve the speech recognition performance. The method is based on introducing time warping algorithms to whole-sentences domains.