Sorry, you need to enable JavaScript to visit this website.

We propose a method for zero-resource domain adaptation of DNN acoustic models, for use in low-resource situations where the only in-language training data available may be poorly matched to the intended target domain. Our method uses a multi-lingual model in which several DNN layers are shared between languages. This architecture enables domain adaptation transforms learned for one well-resourced language to be applied to an entirely different low- resource language.

In this work, we present speech recognition systems for four Ethiopian languages: Amharic, Tigrigna, Oromo and Wolaytta. We have used comparable training corpora of about 20 to 29 hours speech and evaluation speech of about 1 hour for each of the languages. For Amharic and Tigrigna, lexical and language models of different vocabulary size have been developed. For Oromo and Wolaytta, the training lexicons have been used for decoding.

We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through conditioning on past frames and predicting information about future frames. Whereas Mockingjay is designed to predict the current frame through jointly conditioning on both past and future contexts.

We present an effective method to solve a small-footprint keyword spotting (KWS) and voice command based user interface for mobile game. For KWS task, our goal is to design and implement a computationally very light deep neural network model into mobile device, in the same time to improve the accuracy in various noisy environments. We propose a simple yet effective convolutional neural network (CNN) with Google’s tensorflow-lite for android and Apple’s core ML for iOS deployment.

In speaker-aware training, a speaker embedding is appended to DNN input features. This allows the DNN to effectively learn representations, which are robust to speaker variability.
We apply speaker-aware training to attention-based end- to-end speech recognition. We show that it can improve over a purely end-to-end baseline. We also propose speaker-aware training as a viable method to leverage untranscribed, speaker annotated data.

In this paper, we present a Small Energy Masking (SEM) algorithm, which masks inputs having values below a certain threshold. More specifically, a time-frequency bin is masked if the filterbank energy in this bin is less than a certain energy threshold. A uniform distribution is employed to randomly generate the ratio of this energy threshold to the peak filterbank energy of each utterance in decibels. The unmasked feature elements are scaled so that the total sum of the feature values remain the same through this masking procedure.