Title :
Canned speech for tactical voice message systems
Author :
Kang, George S. ; Heide, David A.
Author_Institution :
US Naval Res. Lab., Washington, DC, USA
Abstract :
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
Keywords :
military systems; speech coding; speech synthesis; 100 bit/s; canned speech generation; concatenation; data rate; high-density memory devices; speech waveforms; tactical voice message systems; text-to-speech converter; voice communication; voice encoding; Electronic warfare; Laboratories; Marine vehicles; Message systems; Multimedia systems; Postal services; Research and development; Speaker recognition; Speech; Vocabulary;
Conference_Titel :
Tactical Communications Conference, 1992. Vol. 1 Tactical Communications: Technology in Transition., Proceedings of the
Conference_Location :
Fort Wayne, IN
Print_ISBN :
0-7803-0745-3
DOI :
10.1109/TCC.1992.247166