Context (archaeology)

License

Affine transformation

Pure mathematics

Scripting language

Biology

Hidden Markov model

Operating system

Set (abstract data type)

Computer science

Paleontology

Natural language processing

Mathematics

Documentation

Artificial intelligence

Programming language

Subspace topology

Speech recognition

We describe the design of Kaldi, a free, open-source toolkit for speech recognition research. Kaldi provides a speech recognition system based on finite-state automata (using the freely available OpenFst), together with detailed documentation and a comprehensive set of scripts for building complete recognition systems. Kaldi is written is C++, and the core library supports modeling of arbitrary phonetic-context sizes, acoustic modeling with subspace Gaussian mixture models (SGMM) as well as standard Gaussian mixture models, together with all commonly used linear and affine transforms. Kaldi is released under the Apache License v2.0, which is highly nonrestrictive, making it suitable for a wide community of users.

The Kaldi Speech Recognition Toolkit