r60 - 14 Mar 2008 - 10:31:53 - 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)
  • Sautrela4dummies (spanish)
    1. Un ejemplo completo?
    2. Cómo ejecutar Sautrela?
    3. Bases de datos de audio?
    4. Modelos Ocultos de Markov Continuos?
    5. Autómatas de Estados Finitos Ponderados?
    6. Modelo de Markov por Capas?
  • Sautrela4dummies (english)
    1. A full example
    2. How-to run Sautrela
    3. Acoustic Data Bases
    4. Continuous Hidden Markov Models
    5. Weighted Finite-State Automata
    6. Layered Markov Models
  • ADB Templates?


Sautrela is written and distributed under the GNU General Public License which means that its source code is freely-distributed and available to the general public.

View topic | Edit | Attach | Printable | Raw View | Backlinks: Web, All Webs | History: r65 |r62 < r61 < r60 < r59 | 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