r65 - 07 Jan 2016 - 18:12:02 - MikelPenagarikanoYou are here: TWiki >  Sautrela Web  > WebHome

wip Welcome to the Sautrela Project web wip


Sautrela is a highly modular and pluggable open source framework focused on speech recognition. The aim of Sautrela is to unify in a single framework almost all the tasks related to pattern recognition such as signal processing, model training and decoding.


  • Developed using the Java™ Technology and thus ensures its portability to a large variety of computer platforms.
  • Java Beans based component architecture.
  • Different stochastic model techniques are integrated in a generalized model architecture. Regardless of its internal structure, any model that implements a simple Weighted Finite State Automata (WFSA) interface can be managed by the system.
  • A trainer module? performs the training of any model used by the system through a generic training interface, thus, no external software is needed to train models. This approach drastically simplifies the effort to incorporate new modelling formalisms into the framework.


Sautrela Architecture


  • Api (Javadoc)

Source Code


Sautrela is written and distributed under the BSD 2-Clause License (FreeBSD?/Simplified) which means that its source code is freely-distributed and available to the general public.

Edit | Attach | Printable | Raw View | Backlinks: Web, All Webs | History: r65 < r64 < r63 < r62 < r61 | More topic actions
Arquitectura software y sistema para Procesamiento de Señal orientado a Reconocimeinto Automático del habla A Highly Modular Open Source
Speech Recognition Framework
"debile principium melior fortuna sequatur",Bernat Etxepare, 1545
Copyright © Mikel PenagarikanoValid XHTML 1.0 Transitional