TY - JOUR
T1 - Speech recognition technology
T2 - A critique
AU - Levinson, Stephen E.
PY - 1995/10/24
Y1 - 1995/10/24
N2 - This paper introduces the session on advanced speech recognition technology. The two papers comprising this session argue that current technology yields a performance that is only an order of magnitude in error rate away from human performance and that incremental improvements will bring us to that desired level. I argue that, to the contrary, present performance is far removed from human performance and a revolution in our thinking is required to achieve the goal. It is further asserted that to bring about the revolution more effort should be expended on basic research and less on trying to prematurely commercialize a deficient technology.
AB - This paper introduces the session on advanced speech recognition technology. The two papers comprising this session argue that current technology yields a performance that is only an order of magnitude in error rate away from human performance and that incremental improvements will bring us to that desired level. I argue that, to the contrary, present performance is far removed from human performance and a revolution in our thinking is required to achieve the goal. It is further asserted that to bring about the revolution more effort should be expended on basic research and less on trying to prematurely commercialize a deficient technology.
UR - http://www.scopus.com/inward/record.url?scp=0028832546&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0028832546&partnerID=8YFLogxK
U2 - 10.1073/pnas.92.22.9953
DO - 10.1073/pnas.92.22.9953
M3 - Article
C2 - 7479808
AN - SCOPUS:0028832546
SN - 0027-8424
VL - 92
SP - 9953
EP - 9955
JO - Proceedings of the National Academy of Sciences of the United States of America
JF - Proceedings of the National Academy of Sciences of the United States of America
IS - 22
ER -