EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology
2nd INTERSPEECH Event

Aalborg, Denmark
September 3-7, 2001

                 

DIARCA: A Component Approach to Voice Recognition

Juan C. Díaz Martín (1), Juan L. García Zapata (1), José M. Rodríguez García (1), José F. Álvarez Salgado (1), Pablo Espada Bueno (1), Pedro Gómez Vilda (2)

(1) Universidad de Extremadura, Spain
(2) Universidad de Politécnica de Madrid, Spain

Current voice recognition systems tend to be implemented as a PC desktop facility. This model is not suitable for the growing complexities of present and future developments: It is single-user, it is non portable, and it assumes the workstation model, where all the CPU resources are supposed to be locally available. This work researches how a high performance speech recognition system can be redesigned and implemented as a time-critical network service shared through ordinary data transmission media with three main design goals: Scalability, predictability and POSIX portability. The whole idea has been tested by rebuilding IVORY, a well known robust desktop voice recognition methodology, as a distributed component.

Full Paper

Bibliographic reference.  Martín, Juan C. Díaz / Zapata, Juan L. García / García, José M. Rodríguez / Salgado, José F. Álvarez / Bueno, Pablo Espada / Vilda, Pedro Gómez (2001): "DIARCA: a component approach to voice recognition", In EUROSPEECH-2001, 2393-2396.