Skip to search formSkip to main contentSkip to account menu

The Kaldi Speech Recognition Toolkit

The design of Kaldi is described, a free, open-source toolkit for speech recognition research that provides a speech recognition system based on finite-state automata together with detailed documentation and a comprehensive set of scripts for building complete recognition systems.

Recurrent neural network based language model

Results indicate that it is possible to obtain around 50% reduction of perplexity by using mixture of several RNN LMs, compared to a state of the art backoff language model.
View Paper (opens in a new tab)

Extensions of recurrent neural network language model

Several modifications of the original recurrent neural network language model are presented, showing approaches that lead to more than 15 times speedup for both training and testing phases and possibilities how to reduce the amount of parameters in the model.
View on IEEE (opens in a new tab)

The subspace Gaussian mixture model - A structured model for speech recognition

View via Publisher (opens in a new tab)

Sequence-discriminative training of deep neural networks

Different sequence-discriminative criteria are shown to lower word error rates by 7-9% relative, on a standard 300 hour American conversational telephone speech task.
View Paper (opens in a new tab)

RNNLM - Recurrent Neural Network Language Modeling Toolkit

We present a freely available open-source toolkit for training recurrent neural network based language models. It can be easily used to improve existing speech recognition and machine translation…

Strategies for training large scale neural network language models

This work describes how to effectively train neural network based language models on large data sets and introduces hash-based implementation of a maximum entropy model, that can be trained as a part of the neural network model.
View on IEEE (opens in a new tab)

Empirical Evaluation and Combination of Advanced Language Modeling Techniques

It is concluded that for both small and moderately sized tasks, new state of the art results with combination of models, that is significantly better than performance of any individual model are obtained.
View Paper (opens in a new tab)

Subspace Gaussian Mixture Models for speech recognition

An acoustic modeling approach in which all phonetic states share a common Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of the total parameter space, and this style of acoustic model allows for a much more compact representation.
View on IEEE (opens in a new tab)

Full-covariance UBM and heavy-tailed PLDA in i-vector speaker verification

The use of universal background models (UBM) with full-covariance matrices is suggested and thoroughly experimentally tested and dimensionality reduction of i-vectors before entering the PLDA-HT modeling is investigated.
View on IEEE (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)