We introduce a self-supervised speech pre-training method called TERA, which stands for
Transformer Encoder Representations from Alteration. Recent approaches often learn by …

This survey presents a review of state-of-the-art deep neural network architectures,
algorithms, and systems in speech and vision applications. Recent advances in deep …

Speech data is crucially important for speech recognition research. There are quite some
speech databases that can be purchased at prices that are reasonable for most research …

Human civilizations have performed the art of writing across continents and over different
time periods. In order to speed up the writing process, the art of shorthand (brachygraphy) …

Consider speech recognition. We have a dataset of audio clips and corresponding
transcripts. Unfortunately, we don't know how the characters in the transcript align to the …

Recently, recurrent neural networks (RNN) have achieved the state-of-the-art performance
in several applications that deal with temporal data, eg, speech recognition, handwriting …

In this survey paper, we have evaluated several recent deep neural network (DNN)
architectures on a TIMIT phone recognition task. We chose the TIMIT corpus due to its …

This paper presents a new approach for building Language Models using the Quantum
Probability Theory, a Quantum Language Model (QLM). It mainly shows that relying on this …

Purpose: The Speech Accessibility Project (SAP) intends to facilitate research and
development in automatic speech recognition (ASR) and other machine learning tasks for …

The auditory system converts the physical properties of a sound waveform to neural
activities and processes them for recognition. During the process, the tuning to amplitude …