Welcome to the Sautrela Project web

Introduction

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.

Features

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.

Download

• Sautrela.jar
• Run demo suite (Java WebStart)

Sautrela Architecture

• Engine,
• DataProcessor,
• Layered Markov Model,

Documentation

• Api (Javadoc)

Source Code

• The source code is included in Sautrela.jar

License

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.