Title :
Recognition in a new key-towards a science of spoken language
Author :
Greenberg, Steven
Author_Institution :
Int. Comput. Sci. Inst., Berkeley, CA, USA
Abstract :
Automatic speech recognition in the twenty-first century will strive to emulate many properties of human speech understanding that currently lie beyond the capability of present-day systems. Such future-generation recognition will require massive amounts of empirical data in order to derive the organizational principles underlying the generation and decoding of spoken language. Such data can be efficiently collected through systematic computational experimentation designed to identify the important building blocks of speech and delineate the nature of the structural interactions among linguistic tiers associated with the extraction of semantic information
Keywords :
computational linguistics; natural languages; speech recognition; automatic speech recognition; building blocks; decoding; generation; human speech understanding; linguistic tiers; organizational principles; semantic information; spoken language; structural interactions; Aerospace materials; Automatic speech recognition; Background noise; Computer science; Data mining; Decoding; Degradation; Humans; Natural languages; Speech enhancement;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.675446
