Speech-based e-Education technology allows users to access learning content on the web by dialing a telephone number. Speech-enabled applications, particularly in the domain of education are primarily implemented to cater for the plight of the visually impaired towards addressing the shortcomings of user interface (UI) design of a mobile learner. However, with the increase in learning resources...

For the past few decades, the bane of Automatic Speech Recognition (ASR) systems have been phonemes and Hidden Markov Models (HMMs). HMMs assume conditional independence between observations, and the reliance on explicit phonetic representations requires expensive handcrafted pronunciation dictionaries. Learning is often via detached proxy problems, and there especially exists a disconnect betw...

It is unclear as to how infants learn the acoustic expression of each phoneme of their native languages. In recent studies, researchers have inspected phoneme acquisition by using a computational model. However, these studies have used a limited vocabulary as input and do not handle a continuous speech that is almost comparable to a natural environment. Therefore, we use a natural continuous sp...

In this paper we propose a novel general framework for unsupervised model adaptation. Our method is based on entropy which has been used previously as a regularizer in semi-supervised learning. This technique includes another term which measures the stability of posteriors w.r.t model parameters, in addition to conditional entropy. The idea is to use parameters which result in both low conditio...

This paper presents a new unit selection process for Very Low Bit Rate speech encoding around 500 bits/sec. The encoding is based on speech recognition and speech synthesis technologies. The aim of this approach is to use at best the speech corpus of the speaker. The proposed solution uses HMM modelling for the recognition of elementary speech units. The HMM are first trained in an unsupervised...

In this paper, we propose a novel progressive learning (PL) framework for deep neural network (DNN) based speech enhancement. It aims at decomposing the complicated regression problem of mapping noisy to clean speech into a series of subproblems for enhancing system performances and reducing model complexities. As an illustration, we design a signal-tonoise ratio (SNR) based PL architecture by ...

dependency parsing is a way of syntactic parsing and a natural language that automatically analyzes the dependency structure of sentences, and the input for each sentence creates a dependency graph. part-of-speech (pos) tagging is a prerequisite for dependency parsing. generally, dependency parsers do the pos tagging task along with dependency parsing in a pipeline mode. unfortunately, in pipel...

How do characteristics of caregiver speech contribute to a child’s early word learning? We explore the relationship between a single child’s vocabulary growth and the distributional and prosodic characteristics of the speech he hears using data collected for the Human Speechome Project, an ecologically valid corpus collected from the home of a family with a young child. We measured F0, intensit...

Recently, various unsupervised representation learning approaches have been investigated to produce augmenting features for natural language processing systems in the open-domain learning scenarios. In this paper, we propose a dynamic dependency network model to conduct semi-supervised representation learning. It exploits existing task-specific labels in the source domain in addition to the lar...