Canned speech for tactical voice message systems
George S. Kang, David A. Heide · 2003
Various aspects of canned speech generation were examined. In this approach, brief tactical messages are generated by concatenating the speech waveforms corresponding to the individual words. According to the tests conducted, listeners unanimously preferred canned speech over synthetic speech generated by a text-to-speech converter. They selected canned speech not only for its higher intelligibility, but they also felt that canned speech was more natural. Some listeners thought that canned speech was originally recorded as sentences rather than individual words strung together. The data rate required to transmit canned speech is very low (well below 100 b/s). Such a low-data-rate voice encoding technique is essential when the network is congested. Future voice communication should be designed in such a manner that no voice messages are preempted because any voice call might be delivering vital tactical information. With the availability of low-cost, high-density memory devices, canned speech generation is practical in many applications.>