Patrick M. Commarford

Models of Throughput Rates for Dictation and Voice Spelling for Handheld Devices

Since the emergence of the personal digital assistant (PDA), developers have attempted to create input methods that allow users to enter accurate data at speeds that approach those achieved with the personal computer. Common text entry methods (handwriting and soft keyboard) allow for rates that are unacceptably slow for many purposes. The objective of this paper is to consider the possible benefits of speech-to-text input mechanisms (dictation and voice spelling) for handheld devices. By modeling throughput based on varying rates of speech, correction speeds, and system recognition accuracies, we can compare expected speech throughput rates to current throughput rates for PDAs.

Developing a voice-spelling alphabet for PDAs

A persistent problem with personal digital assistants (PDAs) is the difficulty of entering data into the devices. The best current solutions to the problem are small soft keyboards and constrained handwriting recognizers. Another solution is use of speech. PDAs do not yet have the power to support full speech dictation, but they do have sufficient power to support voice spelling. Voice-spelling problems include the high acoustic confusability between certain letters of the alphabet and the difficulty of memorizing code words for the letters of the alphabet. This paper describes several User-Centered Design studies conducted to develop a voice-spelling alphabet for PDAs that overcomes these problems, including: (1) the development of a model of user performance to assess the potential of voice spelling as an alternate input method for PDAs, (2) Web-based surveys for determining the words that people tend to associate with the letters of the alphabet, (3) accuracy experiments used to tune the final voice-spelling alphabet, and (4) the development of a graphical user interface for displaying code words as a prompt when voice spelling is used. The results of these studies suggest that it would be worthwhile to develop a working voice-spelling system for PDAs in the future.

Handheld Electronic Devices

From PDAs to cell phones to MP3 players, handheld electronic devices are ubiquitous. Human factors engineers and designers have a need to remain informed about advances in research on user interface design for this class of devices. This review provides human factors research summaries and research-based guidelines for the design of handheld devices. The major topics include anthropometry (fitting the device to the hand), input (types of device control and methods for data entry), output (display design), interaction design (one-handed use, scrolling, menu design, image manipulation, and using the mobile Web), and data sharing (among users, devices, and networks). Thus, this review covers the key aspects of the design of handheld devices, from the design of the physical form of the device through its hardware and software, including its behavior in networks.

Web-Based Comparison of Two Styles of Auditory Presentation: All TTS versus Rapidly Mixed Tts and Recordings

A current controversy in the interactive voice response (IVR) community is whether and under which conditions designers should use recorded audio when portions of the interface must be generated by text -to-speech (TTS). The purpose of this study was to examine user preferences for a very extreme case—a prompt that incorporates multiple units of dynamic information in a single sentence. Two groups of IBM employees listened to and compared two auditory styles of information presentation (all information given by a single TTS voice and alternating recorded audio and the TTS voice.) The groups listened to both presentation styles in counterbalanced order and then indicated their preference and degree of preference. The percentage of respondents indicating a preference for the all TTS style was significantly greater than the percentage indicating a preference for the mixture of recorded and TTS.