"... In PAGE 2: ... In effect, most of these designs were mainly concerned with the implementation of the technology instead of exploring the use of psychomotor parameters in the human system. Table1 a. An overview of recent experiments with new musical instrument designs.... In PAGE 2: ...o.) STEIM, Amsterdam, the Netherlands Web MIDI controller (straingauge based) Michel Waisvisz, STEIM (see Krefeld, 1990) Hands MIDI controller (buttons, ultrasound ranging and mercury switches) Steve O apos;Hearn, Rhode Island School of design, USA, see Moog (1989) Design of a new stick-like MIDI controller, with pressure sensitive buttons) Table1 b. An overview of recent experiments with devices for conducting.... In PAGE 3: ... Table1 d. An overview of experiments with new musical instrument designs involving whole body movements.... In PAGE 3: ...able 1d. An overview of experiments with new musical instrument designs involving whole body movements. Author Motion to sound design Leon Theremin (see Vail, 1993) Capacitively coupled motion detector controls electronic oscillator Chabot (1990) Ultrasound ranging to detect whole body movements and to control MIDI devices Bauer amp; Foss (1992) GAMS: Ultrasound ranging to detect whole body movements and to control MIDI devices Leslie-Ann Coles, USA Bodysuit performance during CHI 92 Coniglio (1992) MIDIDancer bodysuit / Interactor mapping software Yamaha Corp., Japan MIBURI: arm gestures, finger buttons to MIDI translation David Rokeby, Toronto, Canada Very Nervous System: video image processor translates movement into MIDI Fred Kolman, Amsterdam, the Netherlands Video image processor translates movement into MIDI Camurri (1987) Costel opto-electronic human movement tracking system controls a knowledge based computer music system Table1 e. An overview of experiments with new musical instrument designs involving bioelectric signals.... ..."

"... In PAGE 2: ... Additional buttons, located along the index finger, are used to produce more than the 25 distinct characters. Figure 1 shows the external appearance of Chording Glove and Table1 shows the key map of the Chording Glove for the English language. ... ..."

"... In PAGE 12: ... We tested all systems by simulating each user signing every word in the English dictionary. The results are shown in the first line of Table4 . With the help of a bigram context, 1Our experience is that this makes a significant difference in the performance of the recognition system.... In PAGE 14: ... The goal is to determine whether our system could be extended to recognize these new templates, even though they were not in the training set of the gesture recognizers. With the complete training set, our approach achieved 73% accuracy with context, and 62% without, as shown on the first line of Table4 . We successively removed every letter from the training set, one at a time, and found that the average accuracy across all twenty-four letters was 66% with context, and 57% without.... ..."

"... In PAGE 6: ... We tested all systems by us- ing probabilistically generated sequences of signed letters, based on the English dictionary. The results are shown in the first line of Table3 . Our system performed comparably to the baseline, and the addition of context improved perfor- mance significantly.... ..."