- 39 Downloads
From its earliest conception, virtual reality was meant to be an all encompassing multimodal experience. Indeed, the modalities that are the concern of this special issue, speech and gesture, were foremost in the minds of the very earliest researchers. Over 20 years ago, there was significant optimism as to the expected rate of progress of both speech and vision research, and unencumbered interfaces to immersive systems were considered highly likely in the near future.
Speech-based interfaces have always been at the top of the virtual reality researcher’s “must have” list. The ability to give and receive spoken instructions obviates the need for physical input devices for a range of actions, and thus has great potential to enhance the sense of presence experienced by a user. These days both speech recognition and speech synthesis can be treated as off-the-shelf technologies. However, whilst robustness of speech recognition, and the naturalness of speech synthesis, have come a long way...