Truncation error and dynamics in very low latency phonetic recognition
2003 (English)In: Proceedings of Non Linear Speech Processing (NOLISP), 2003Conference paper (Refereed)
The truncation error for a two-pass decoder is analyzed in a problem of phonetic speech recognition for very demanding latency constraints (look-ahead length < 100ms) and for applications where successive renements of the hypotheses are not allowed. This is done empirically in the framework of hybrid MLP/HMM models. The ability of recurrent MLPs, as a posteriori probability estimators, to model time variations is also considered, and its interaction with the dynamic modeling in the decoding phase is shown in the simulations.
Place, publisher, year, edition, pages
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-53572OAI: oai:DiVA.org:kth-53572DiVA: diva2:470365
NOLISP 03. Le Croisic, France. May 20-23, 2003
QC 201201032011-12-282011-12-282012-01-03Bibliographically approved