The limits of speech recognition: Understanding acoustic memory and appreciating prosody (2000)

Abstract

Human-human relationships are rarely a good model for the design of effective user interfaces. Spoken language is effective for human-human interaction (HHI), but it often has severe limitations when applied to human-computer interaction (HCI). Speech is slow for presenting information, it is difficult to review or edit, and it interferes with other cognitive tasks. However speech has proven to be useful for store-and-forward messages, alerts in busy environments, and input-output for blind or motor-impaired users. Speech recognition for control is helpful for hands-busy, eyes-busy, mobilityrequired, or hostile environments and it shows promise for use in telephone-based services. Dictation input is increasingly accurate, but adoption outside the disabled users community has been slow compared to visual interfaces. Obvious physical problems include fatigue from speaking continuously and the disruption in an office filled with people speaking. <p>By understanding the cognitive processes surrounding human acoustic memory and processing, interface designers may be able to integrate speech more effectively and guide users more successfully. Then by appreciating the differences between HHI and HCI designers may be able to choose appropriate applications for human use of speech with computers. The key distinction may be the rich emotional content conveyed by prosody -- the pacing, intonation, and amplitude in spoken language. Prosody is potent for HHI, but may be disruptive for HCI.