The application of dynamic programming to connected speech recognition

1990 ◽  
Vol 7 (3) ◽  
pp. 6-25 ◽  
Author(s):  
H.F. Silverman ◽  
D.P. Morgan
Keyword(s):  
Dynamic Programming ◽  
Speech Recognition ◽  
Connected Speech

A unified alignment algorithm for bilingual data

2011 ◽  
Vol 19 (1) ◽  
pp. 33-60 ◽  
Author(s):  
CHRISTOPH TILLMANN ◽  
SANJIKA HEWAVITHARANA
Keyword(s):  
Dynamic Programming ◽  
Speech Recognition ◽  
Search Algorithm ◽  
Alignment Algorithm ◽  
Comparable Data ◽  
Beam Search ◽  
Sentence Level ◽  
Unified Algorithm ◽  
The One ◽  
Document Level

AbstractThe paper presents a novel unified algorithm for aligning sentences with their translations in bilingual data. With the help of ideas from a stack-based dynamic programming decoder for speech recognition (Ney 1984), the search is parametrized in a novel way such that the unified algorithm can be used on various types of data that have been previously handled by separate implementations: the extracted text chunk pairs can be either sub-sentential pairs, one-to-one, or many-to-many sentence-level pairs. The one-stage search algorithm is carried out in a single run over the data. Its memory requirements are independent of the length of the source document, and it is applicable to sentence-level parallel as well as comparable data. With the help of a unified beam-search candidate pruning, the algorithm is very efficient: it avoids any document-level pre-filtering and uses less restrictive sentence-level filtering. Results are presented on a Russian–English, a Spanish–English, and an Arabic–English extraction task. Based on simple word-based scoring features, text chunk pairs are extracted out of several trillion candidates, where the search is carried out on 300 processors in parallel.

Sign in / Sign up

Export Citation Format

Share Document