The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In massive multiple-input multiple-output (MIMO) systems, superimposed (SP) and time-multiplexed (TM) pilots exhibit a complementary behavior, with the former and latter schemes offering a higher throughput in high and low inter-cell interference scenarios, respectively. Based on this observation, in this paper, we propose an algorithm for partitioning users into two disjoint sets comprising users...
This paper introduces a pre-training technique for learning discriminative features from electroencephalography (EEG) recordings using deep neural networks. EEG data are generally only available in small quantities, they are high-dimensional with a poor signal-to-noise ratio, and there is considerable variability between individual subjects and recording sessions. Similarity-constraint encoders as...
It is known that applying a time-frequency binary mask to very noisy speech can improve its intelligibility but results in poor perceptual quality. In this paper we propose a new approach to applying a binary mask that combines the intelligibility gains of conventional binary masking with the perceptual quality gains of a classical speech enhancer. The binary mask is not applied directly as a time-frequency...
This paper addresses the task of Automatic Speech Recognition (ASR) with music in the background, where the accuracy of recognition may deteriorate significantly. To improve the robustness of ASR in this task, e.g. for broadcast news transcription or subtitles creation, we adopt two approaches: 1) multi-condition training of the acoustic models and 2) denoising autoencoders followed by acoustic model...
Millimeter-wave (mmWave) systems require massive antennas at both transmitter and receiver to reach desirable link budget. Analog-digital hybrid beamforming is a promising architecture since it significantly reduces the hardware cost while approaches the performance of digital beamforming. However, the nonlinear power amplifier (PA) introduces intermodulation interference and degrades the spectral...
Microprocessors and FPGAs need to enable simpler and compact platforms via integration of self-contained test and training circuits, training of data interface buffers for process and temperature variation being a prime example. This paper studies package embedding of resistors for buffer tuning and presents a scheme to utilize a single resistor to train a large number of buffers without increase...
In this study, we explore long short-term memory recurrent neural networks (LSTM-RNNs) for speech enhancement. First, a regression LSTM-RNN approach for a direct mapping from the noisy to clean speech features is presented and verified to be more effective than deep neural network (DNN) based regression techniques in modeling long-term acoustic context. Then, a comprehensive comparison between the...
This paper addresses the problem of Target Activity Detection (TAD) for binaural listening devices. TAD denotes the problem of robustly detecting the activity of a target speaker in a harsh acoustic environment, which comprises interfering speakers and noise ('cocktail party scenario'). In previous work, it has been shown that employing a Feed-forward Neural Network (FNN) for detecting the target...
We address the problem of learning an efficient and adaptive physical layer encoding to communicate binary information over an impaired channel. In contrast to traditional work, we treat the problem an unsupervised machine learning problem focusing on optimizing reconstruction loss through artificial impairment layers in an autoencoder (we term this a channel autoencoder) and introduce several new...
Computational auditory scene analysis (CASA) system is well used in speech enhancement area in recent years. We propose a new system that combines CASA and spectral subtraction to get better enhanced speech. The CASA part consists of the latest method deep neural networks (DNNs). The original way to reconstruct the denoise signal is to use the estimated masks with direct overlap-add method ignoring...
This paper proposes a new detection scheme for concealed micro-electronic devices by analyzing harmonic waves which are reflected from targets with classification restricted Boltzmann machine algorithm (Class/RBM). This new method exploits the characteristics of the second and the third harmonics waves to classify metal and electronic devices, as is done in all other Pdetection schemes. Moreover the...
Millimeter wave (mmWave) is an attractive option for high data rate applications. Enabling mmWave communications requires appropriate beamforming, which is conventionally realized by a lengthy beam training process. Such beam training will be a challenge for applying mmWave to mobile environments. As a solution, a beam tracking method requiring to train only one beam pair to track a path in the analog...
The abundant spectrum at millimeter-wave (mmWave) has the potential to greatly increase the capacity of 5G cellular systems. However, to overcome the high pathloss in the mmWave frequencies, beamforming with large antenna arrays is required at both the base station and user equipments for sufficient link budget. This feature is a challenge for beamforming training during initial access due to low...
In this paper we propose to use a state-of-the-art Deep Recurrent Neural Network (DRNN) based Speech Enhancement (SE) algorithm for noise robust Speaker Verification (SV). Specifically, we study the performance of an i-vector based SV system, when tested in noisy conditions using a DRNN based SE front-end utilizing a Long Short-Term Memory (LSTM) architecture. We make comparisons to systems using...
In speaker recognition, the mismatch between the enrollment and test utterances due to noise with different signal-to-noise ratios (SNRs) is a great challenge. Based on the observation that noise-level variability causes the i-vectors to form heterogeneous clusters, this paper proposes using an SNR-aware deep neural network (DNN) to guide the training of PLDA mixture models. Specifically, given an...
This paper considers training-based transmissions in massive multi-input multi-output (MIMO) systems with one-bit analog-to-digital converters (ADCs). We assume that each coherent transmission block consists of a pilot training stage and a data transmission stage. The base station (BS) first employs the linear minimum mean-square-error (LMMSE) method to estimate the channel and then uses the maximum-ratio...
5G wireless standards require a much lower latency than what current wireless systems can guarantee. The main challenge to fulfill this requirement is the capability to support short packet transmission, in contrast to most of the current standards which use a long data packet structure. In this paper, we propose an efficient receiver technique that exploits information obtained during the data transmission...
In this study, we investigate on the learning behaviors of DNN by explicit feature transformations. As a demonstration, linear and logarithm transformations, corresponding to the amplitude spectra and log-power spectra, are compared with the same minimum mean squared error (MMSE) objective function for optimizing DNN parameters. Based on the experimental analysis of the DNN learning behaviors, we...
This paper proposes a novel framework that integrates audio and visual information for speech enhancement. Most speech enhancement approaches consider audio features only to design filters or transfer functions to convert noisy speech signals to clean ones. Visual data, which provide useful complementary information to audio data, have been integrated with audio data in many speech-related approaches...
In this study, we propose a regression approach via deep neural network (DNN) for unsupervised speech separation in a single-channel setting. We rely on a key assumption that two speakers could be well segregated if they are not too similar to each other. A dissimilarity measure between two speakers is then proposed to characterize the separation ability between competing speakers. We demonstrate...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.