A reusable HMM soft-core for isolated word recognition

Author

Rodellar, V. ; Gonzalez-Concejero, C. ; Carretero, P. ; Alvarez-Marquina, A. ; Gomez-Vilda, P.

Author_Institution

Departamento de Arquitectura y Tecnologia de Sistemas Informaticos, Univ. Politecnica de Madrid, Spain

Volume

1

fYear

2005

fDate

14-15 July 2005

Firstpage

303

Abstract

In this paper we introduce a scalable and reusable library component implementation of a HMM that may be used in order to be embedded in the full chain of an isolated word recognition system. Theoretically, the core allows for an unlimited ™scalability in the number of the vocabulary words (L) and in the number of symbols in the observation sequence of the word to be recognized (O). The number of hidden states (N) is also scalable, but limited to 16 and organized as a Bakis´ model. The hardware design has been modeled in VHDL portable code resulting in a technology independent soft-core.

Keywords

hardware description languages; hidden Markov models; text analysis; VHDL portable code; hardware design; isolated word recognition system; reusable HMM soft core; vocabulary words; Application software; Design automation; Hardware; Hidden Markov models; Intellectual property; Scalability; Software libraries; Speech synthesis; Time to market; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Circuits and Systems, 2005. ISSCS 2005. International Symposium on

Print_ISBN

0-7803-9029-6

Type

conf

DOI

10.1109/ISSCS.2005.1509914

Filename

1509914