Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition but still remains an important challenge …
A key learning scenario in large-scale applications is that of federated learning, where a centralized model is trained based on data originating from a large number of clients. We …
In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples …
Z Wang, T Oates - Workshops at the twenty-ninth AAAI conference on …, 2015 - cdn.aaai.org
Inspired by recent successes of deep learning in computer vision and speech recognition, we propose a novel framework to encode time series data as different types of images …
While biometric authentication has advanced significantly in recent years, evidence shows the technology can be susceptible to malicious spoofing attacks. The research community …
Successful speech perception requires that listeners map the acoustic signal to linguistic categories. These mappings are not only probabilistic, but change depending on the …
In real-world applications of visual recognition, many factors-such as pose, illumination, or image quality-can cause a significant mismatch between the source domain on which …
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 transducers (using the …
X Cui, V Goel, B Kingsbury - IEEE/ACM Transactions on Audio …, 2015 - ieeexplore.ieee.org
This paper investigates data augmentation for deep neural network acoustic modeling based on label-preserving transformations to deal with data sparsity. Two data …