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 Architecture
Documentation
Source Code
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.