Deep neural networks (DNN) are currently very successful for acoustic modeling in ASR systems. One of the main challenges with DNNs is unsupervised speaker adaptation from an initial speaker clustering, because DNNs have a very large number of parameters. Recently, a method has been proposed to adapt DNNs to speakers by combining speaker-specific information (in the form of i-vectors computed a...

This paper presents and examines multifeature modular deep neural network acoustic models. The proposed setup uses well trained bottleneck networks to extract features from multiple combinations of input features and combines them using a classification deep neural network (DNN). The effectiveness of each feature combination is evaluated empirically on multiple test sets for both a classical DN...

Deep neural networks (DNNs) have been recently introduced in speech synthesis. In this paper, an investigation on the importance of input features and training data on speaker dependent (SD) DNN-based speech synthesis is presented. Various aspects of the training procedure of DNNs are investigated in this work. Additionally, several training sets of different size (i.e., 13.5, 3.6 and 1.5 h of ...

We developed task-optimized deep neural networks (DNNs) that achieved state-ofthe-art performance in different evaluation scenarios for automatic music tagging. These DNNs were subsequently used to probe the neural representations of music. Representational similarity analysis revealed the existence of a representational gradient across the superior temporal gyrus (STG). Anterior STG was shown ...

abstract autoregressive integrated moving average (arima) has been one of the widely used linear models in time series forecasting during the past three decades. recent studies revealed the superiority of artificial neural network (ann) over traditional linear models in forecasting. but neither arima nor anns can be adequate in modeling and forecasting time series since the first model cannot d...

Multi-task learning (MTL) can be an effective way to improve the generalization performance of singly learning tasks if the tasks are related, especially when the amount of training data is small. Our previous work applied MTL to the joint training of triphone and trigrapheme acoustic models using deep neural networks (DNNs) for low-resource speech recognition. Significant recognition improveme...

Infants' speech perception adapts to the phonemic categories of their native language, a process assumed to be driven by the distributional properties of speech. This study investigates whether deep neural networks (DNNs), the current state-of-the-art in distributional feature learning, are capable of learning phoneme-like representations of speech in an unsupervised manner. We trained DNNs wit...

Deep neural networks (DNNs) are currently widely used for many artificial intelligence (AI) applications including computer vision, speech recognition, and robotics. While DNNs deliver state-ofthe-art accuracy on many AI tasks, it comes at the cost of high computational complexity. Accordingly, there has been a significant amount of research on the topic of energy-efficient processing of DNNs, ...

Deep learning using multi-layer neural networks (NNs) architecture manifests superb power in modern machine learning systems. The trained Deep Neural Networks (DNNs) are typically large. The question we would like to address is whether it is possible to simplify the NN during training process to achieve a reasonable performance within an acceptable computational time. We presented a novel appro...