Kaldi is an open-source speech recognition toolkit written in C++ for speech recognition and signal processing, freely available under the Apache License v2.0.

This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these template messages) The topic of this article may not meet Wikipedia's notability guidelines for products and services. (October 2022) This article relies excessively on references to primary sources. (October 2022)

Kaldi aims to provide software that is flexible and extensible,^[2] and is intended for use by automatic speech recognition (ASR) researchers for building a recognition system.

It supports linear transforms, MMI, boosted MMI and MCE discriminative training, feature-space discriminative training, and deep neural networks.^[3]

Kaldi is capable of generating features like mfcc, fbank, fMLLR, etc. Hence in recent deep neural network research, a popular usage of Kaldi is to pre-process raw waveform into acoustic feature for end-to-end neural models.

Kaldi has been incorporated as part of the CHiME Speech Separation and Recognition Challenge over several successive events.^[4][5][6] The software was initially developed as part of a 2009 workshop at Johns Hopkins University.^[7]

Kaldi is named after the legendary Ethiopian goat herder Kaldi who was said to have discovered the coffee plant.^[8]

• fMLLR
• List of speech recognition software