Skip to search formSkip to main contentSkip to account menu

Librispeech: An ASR corpus based on public domain audio books

It is shown that acoustic models trained on LibriSpeech give lower error rate on the Wall Street Journal (WSJ) test sets than models training on WSJ itself.
View on IEEE (opens in a new tab)

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.

X-Vectors: Robust DNN Embeddings for Speaker Recognition

This paper uses data augmentation, consisting of added noise and reverberation, as an inexpensive method to multiply the amount of training data and improve robustness of deep neural network embeddings for speaker recognition.
View on IEEE (opens in a new tab)

A time delay neural network architecture for efficient modeling of long temporal contexts

This paper proposes a time delay neural network architecture which models long term temporal dependencies with training times comparable to standard feed-forward DNNs and uses sub-sampling to reduce computation during training.
View Paper (opens in a new tab)

The HTK book version 3.4

MUSAN: A Music, Speech, and Noise Corpus

This report introduces a new corpus of music, speech, and noise suitable for training models for voice activity detection (VAD) and music/speech discrimination and demonstrates use of this corpus on Broadcast news and VAD for speaker identification.
View PDF on arXiv (opens in a new tab)

Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI

.
View via Publisher (opens in a new tab)

Minimum Phone Error and I-smoothing for improved discriminative training

The Minimum Phone Error (MPE) and Minimum Word Error (MWE) criteria are smoothed approximations to the phone or word error rate respectively and I-smoothing which is a novel technique for smoothing discriminative training criteria using statistics for maximum likelihood estimation (MLE).
View on IEEE (opens in a new tab)

Deep Neural Network Embeddings for Text-Independent Speaker Verification

These are the best results reported for speaker-discriminative neural networks when trained and tested on publicly available corpora, and the two representations are complementary, and their fusion improves on the baseline at all operating points.
View via Publisher (opens in a new tab)

Boosted MMI for model and feature-space discriminative training

A modified form of the maximum mutual information (MMI) objective function which gives improved results for discriminative training by boosting the likelihoods of paths in the denominator lattice that have a higher phone error relative to the correct transcript.
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)