In recent years, the use of electroencephalography (EEG) has grown as a tool for diagnostic and brain function monitoring, being simple non-invasive method compared with other procedures like histological sampling. Typically, in order to extract functional responses from EEG signals, prolonged repeated stimuli are needed because artifacts generated recordings which adversely impact stimulus-res...

Millions of Foreign Language (FL) learners spend many years learning English in the classroom. Most FL learners learn English in their countries with local teachers, with little or no native L2 input. The Perceptual Assimilation Model (PAM) (Best, 1995, 1999) and Speech Learning Model (SLM) (Flege, 1995) are the most widely used L2 models in L2 speech analysis. However, ...

This paper presents a new discriminative approach for training Gaussian mixture models (GMMs) of hidden Markov models (HMMs) based acoustic model in a large vocabulary continuous speech recognition (LVCSR) system. This approach is featured by embedding a rival penalized competitive learning (RPCL) mechanism on the level of hidden Markov states. For every input, the correct identity state, calle...

Deep learning approaches to problems in speech recognition, computational chemistry, and natural language text processing George Edward Dahl Doctor of Philosophy Graduate Department of Computer Science University of Toronto 2015 The deep learning approach to machine learning emphasizes high-capacity, scalable models that learn distributed representations of their input. This dissertation demons...

Automatic speech recognition has long been a considered dream. While ASR does work today, and it is commercially available, it is extremely sensitive to noise, talker variations, and environments. The current state-of-the-art automatic speech recognizers are based on generative models that capture some temporal dependencies such as hidden Markov models (HMMs). While HMMs have been immensely imp...

Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction between humans and machines. Recently, researchers have demonstrated powerful attacks against machine learning models that can fool them to produce incorrect r...

To objectively evaluate the performance of text-to-speech (TTS) systems, many studies have been conducted in the straightforward way to compare synthesized speech and natural speech with the alignment. However, in most situations, there is no natural speech can be used. In this paper, we focus on machine learning approaches for the TTS evaluation. We exploit a subspace decomposition method to s...

This chapter presents a tool for collaborative elearning using handheld devices that incorporates pair communication via text and speech input. It discusses the current state of e-learning for mobiles and illustrates the lack of such tools in reading comprehension domains. It then describes the tool development as a model for interface design, communication strategies, and data manipulation acr...

In this paper we present some experiments using a deep learning model for speech denoising. We propose a very lightweight procedure that can predict clean speech spectra when presented with noisy speech inputs, and we show how various parameter choices impact the quality of the denoised signal. Through our experiments we conclude that such a structure can perform better than some comparable sin...

We introduce Whistler, a trainable Text-to-Speech (TTS) system, that automatically learns the model parameters from a corpus. Both prosody parameters and concatenative speech units are derived through the use of probabilistic learning methods that have been successfully used for speech recognition. Whistler can produce synthetic speech that sounds very natural and resembles the acoustic and pro...