In recent years, automatic speech recognition has enjoyed tremendous improvements from the use of (deep) neural networks (DNNs) for both acoustic modeling and stochastic language modeling [1, 2]. Powerful hardware, in particular graphics processing units (GPUs), and sophisticated training algorithms enable the use of deeper and deeper networks that reduce word error rates achieved with conventi...

The audio mixing process is an art that has proven to be extremely hard to model: What makes a certain mix better than another one? How can the mixing processing chain be automatically optimized to obtain better results in a more efficient manner? Over the last years, the scientific community has exploited methods from signal processing, music information retrieval, machine learning, and more r...

Motivated by recent gains in speaker identification by incorporating senone posteriors from deep neural networks (DNNs) into i-vector extraction, we examine similar enhancements to speaker diarization with i-vector clustering. We examine two DNNs with different numbers of senone targets in combination with a diagonal or full covariance universal background model (UBM) in the context of the mult...

geological facies interpretation is essential for reservoir studying. the method of classification and identification seismic traces is a powerful approach for geological facies classification and distinction. use of neural networks as classifiers is increasing in different sciences like seismic. they are computer efficient and ideal for patterns identification. they can simply learn new algori...

This paper proposes a discrete recurrent neural network model to implement winner-take-all function. This network model has simple organizations and clear dynamic behaviours. The dynamic properties of the proposed winner-take-all networks are studied in detail. Simulation results are given to show network performance. Since the network model is formulated as discrete time systems , it has advan...

This paper proposes a time-varying heterogeneous alternation controller for the synchronization of delayed neural networks (DNNs). Different from mixture traditional impulse and intermittent control, we consider which is more representative than periodic or aperiodic controllers. To make system under study applicable, impact delay. After doing theoretical analysis, sufficient condition DNNs obt...

Deep Neural Networks (DNNs) have recently outperformed traditional object recognition algorithms on multiple largescale datasets, such as ImageNet. However, the model trained on ImageNet fails on recognising the sketches, because the data source is dominated by photos and all kinds of sketches are roughly labelled as ‘cartoon’ rather than their own categorises (e.g., ‘cat’). Most of sketch reco...