Title :
Connected speech recognition on a multiple processor pipeline
Author :
Chatterjee, Siddhartha ; Agrawal, Prathima
Author_Institution :
Dept. of Comput. Sci., Carnegie-Mellon Univ., Pittsburgh, PA, USA
Abstract :
The authors report on efforts to put a connected speech recognition application on the MARS hardware accelerator. The beam-search algorithm chosen for this purpose was decomposed on a functional basis, not on a data-partitioning basis as in other attempts. This allows for easy synchronization and static load balancing. Further flexibility is provided by retaining the hierarchical structure of the speech graph. The implementation is being tested on a 1000-word vocabulary and preprocessed input data
Keywords :
pipeline processing; speech recognition; 1000-word vocabulary; MARS hardware accelerator; beam-search algorithm; connected speech recognition; data-partitioning; hierarchical structure; multiple processor pipeline; speech graph; static load balancing; synchronization; Clustering algorithms; Data structures; Hardware; Mars; Message passing; Partitioning algorithms; Pipelines; Speech recognition; Switches; Vocabulary;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Conference_Location :
Glasgow
DOI :
10.1109/ICASSP.1989.266542
