We present a simple noise injection algorithm for training end-to-end ASR models which
consists in adding to the spectra of training utterances the scaled spectra of random …

Mixup is a recently proposed technique that creates virtual training examples by combining
existing ones. It has been successfully used in various machine learning tasks. This paper …

In this paper, we study an application of transfer learning approach to speaker's age and
gender recognition task. Recently, speech analysis systems, which take images of log Mel …

Recently, data-driven based Automatic Speech Recognition (ASR) systems have achieved
state-of-the-art results. And transfer learning is often used when those existing systems are …

The hidden activation functions inside deep neural networks (DNNs) play a vital role in
learning high level discriminative features and controlling the information flows to track …

It is an effective way that improves the performance of the existing Automatic Speech
Recognition (ASR) systems by retraining with more and more new training data in the target …

Acoustic-to-articulatory inversion predicting articulatory movement based on the acoustic
signal is useful for many applications like talking head, speech recognition, and education …

In interpersonal co-located and online teaching, lecturers highlight words and sentences in
their speech in order to implicitly communicate that particular content is important. This …

When people get stressed in nervous or unfamiliar situations, their speaking styles or
acoustic characteristics change. These changes are particularly emphasized in certain …

Recently, attention based sequence-to-sequence model become a research hotspot in
speech recognition. The attention model has the problem of slow convergence and poor …