Skip to search formSkip to main contentSkip to account menu
Librispeech: An ASR corpus based on public domain audio books
TLDR
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
Recurrent neural network based language model
TLDR
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
X-Vectors: Robust DNN Embeddings for Speaker Recognition
TLDR
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
A time delay neural network architecture for efficient modeling of long temporal contexts
TLDR
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
Extensions of recurrent neural network language model
TLDR
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
Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI
TLDR
A method to perform sequencediscriminative training of neural network acoustic models without the need for frame-level cross-entropy pre-training is described, using the lattice-free version of the maximum mutual information (MMI) criterion: LF-MMI.
View via Publisher
JHU-ISI Gesture and Skill Assessment Working Set ( JIGSAWS ) : A Surgical Activity Dataset for Human Motion Modeling
TLDR
A dataset of surgical activities captured using the da Vinci Surgical System and consisting of kinematic and video from eight surgeons with different levels of skill performing five repetitions of three elementary surgical tasks on a bench-top model is described.
Deep Neural Network Embeddings for Text-Independent Speaker Verification
TLDR
It is found that the embeddings outperform i-vectors for short speech segments and are competitive on long duration test conditions, which are the best results reported for speaker-discriminative neural networks when trained and tested on publicly available corpora.
View via Publisher
Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks
TLDR
A factored form of TDNNs (TDNN-F) is introduced which is structurally the same as a TDNN whose layers have been compressed via SVD, but is trained from a random start with one of the two factors of each matrix constrained to be semi-orthogonal.
View via Publisher
Audio augmentation for speech recognition
TLDR
This paper investigates audio-level speech augmentation methods which directly process the raw signal, and presents results on 4 different LVCSR tasks with training data ranging from 100 hours to 1000 hours, to examine the effectiveness of audio augmentation in a variety of data scenarios.
View Paper
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License