Abstract: A mount for supporting a microphone on a helmet having an outer shell and for use with a transmission cable. The microphone is mounted on a flexible boom carrying leads connected to the microphone. The transmission cable carries electrical conductors. The mount includes an attachment assembly having a surface with a contour which conforms to the outer shell of the helmet. The attachment assembly is provided with a sleeve-like member adapted to receive the flexible boom and a retainer for receiving the transmission cable. Connectors are carried within the attachment assembly for electrically connecting the electrical conductors from the transmission cable to the leads to the microphone. A layer of an adhesive material is carried by the surface of the attachment assembly and is adapted to fasten the attachment assembly to the outer shell of the helmet. The layer of adhesive material permits the fastening of the attachment assembly to the helmet without impairing the structural integrity of the helmet.

Abstract: Speaker independent recognition of small vocabularies, spoken over the long distance telephone network, is achieved using two types of models, one type for defined vocabulary words (e.g., collect, calling-card, person, third-number and operator), and one type for extraneous input which ranges from non-speech sounds to groups of non-vocabulary words (e.g. `I want to make a collect call please`). For this type of key word spotting, modifications are made to a connected word speech recognition algorithm based on state-transitional (hidden Markov) models which allow it to recognize words from a pre-defined vocabulary list spoken in an unconstrained fashion. Statistical models of both the actual vocabulary words and the extraneous speech and background noises are created. A syntax-driven connected word recognition system is then used to find the best sequence of extraneous input and vocabulary word models for matching the actual input speech.