Abstract
In syntax directed speech recognition communication between the acoustic and syntactic processors of the system causes the acoustic analyzer to evaluate only those grammatically correct word hypotheses generated by the syntax analysis algorithm. Two such systems are discussed which are much faster, but no less accurate than, systems in which the acoustic and syntactic-analyses are sequential and isolated. Theoretical details of the systems are given and experimental results of tests are presented. Methods for using syntax directed recognition to improve overall system accuracy are discussed, showing the relevance of the methods to the recognition of connected speech.
Original language | English (US) |
---|---|
Pages | 700-703 |
Number of pages | 4 |
State | Published - 1978 |
Externally published | Yes |
Event | Rec IEEE Int Conf Acoust Speech Signal Process 3rd - Tulsa, OK, USA Duration: Apr 10 1978 → Apr 12 1978 |
Conference
Conference | Rec IEEE Int Conf Acoust Speech Signal Process 3rd |
---|---|
City | Tulsa, OK, USA |
Period | 4/10/78 → 4/12/78 |
ASJC Scopus subject areas
- General Engineering