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.
A major challenge in realising a full-duplex (FD) transceiver is to decode the received signal in presence of the strong transmit signal termed as self-interference (SI). Usually SI is suppressed by reconstructing it using the transmit signal and subtracting it at the FD receiver. For good cancellation, an accurate estimate of the SI channel is essential. However, training for obtaining the SI channel...
This paper aims to evaluate the system level performance of the newly proposed non-orthogonal multiple access scheme sparse code multiple access (SCMA) with uplink grant-free transmissions for 5G massive machine-type communication (mMTC) scenario. The challenge lies in the modeling and abstraction of physical layer actions as the link-to-system interface, including the features of overloading, grant-free...
With the reuse of identical training sequences by users in different cells, massive MIMO is severely affected by pilot contamination due to residual error in channel estimation. In this paper, we consider the traditional structure of the training phase, where orthogonal pilot sequences are reused, and analyze a recently proposed group- blind detector in the uplink of an interference- limited network...
Spectrum sensing is one of the key technologies of cognitive radio. Based on noise characteristics estimation and support vector machine (SVM) technology, this paper proposed a frequency domain two-stage spectrum sensing method to improve sensing accuracy under low signal-to-noise ratio scenarios with low system complexity and high generalization ability. In the slow sensing stage, the frequency-domain...
In the presence of environmental noise, speaker verification systems inevitably see a decrease in performance. This paper proposes the (1) use of two parallel classifiers, (2) feature enhancement based on blind signal-to-noise ratio (SNR) estimation and (3) fusion, to improve the performance of speaker verification systems. The two classifiers are based on Gaussian mixture models and the partial least-squares...
Orthogonal frequency division multiplexing (OFDM) is one important technologies of power line communication (PLC). This paper presents a new timing synchronization method for OFDM system which can be used in PLC. The proposed timing method is performed by calculating the correlation between the received signal and a local training sequence which is the same as the training sequence of OFDM signal...
This work encompasses Rate-Splitting (RS), providing significant benefits in multi-user settings in the context of huge degrees of freedom promised by massive Multiple-Input Multiple-Output (MIMO). However, the requirement of massive MIMO for cost-efficient implementation makes them more prone to hardware imperfections such as phase noise (PN). As a result, we focus on a realistic broadcast channel...
In P300 speller brain-computer interface (BCI), the stimulus sequence is presented to subject for several rounds to achieve reliable P300 detection. Traditionally, the number of rounds is fixed and relatively large (e.g., 15 in the Wadsworth Dataset of BCI Competition 2005), which results in low information transfer rate. In order to improve the speed of character recognition without affecting the...
This paper develops a novel channel estimation approach for multi-user millimeter wave (mmWave) wireless systems with large antenna arrays. By exploiting the inherent mmWave channel sparsity, we propose a novel simultaneous-estimation with iterative fountain training (SWIFT) framework, in which the average number of channel measurements is adapted to various channel conditions. To this end, the base...
millimeter wave (mmW) communication systems have the potential to increase data rates with low-latency, highly directional communication links. Due to the geometric nature of the propagation, mmW signals can also be used for accurate positioning. This paper explores the trade-off between communication rate and positioning quality in mmW systems. We show how rate and positioning quality interact as...
Millimeter wave (mm-wave) system performance may be degraded if the operation mechanism is not properly designed, because mm-wave systems suffer severe path loss and very short coherence time. Thanks to the sparse channel model and directional transmission property, it is usually sufficient to use analog beam codebooks in beam training to estimate dominant channel components instead of complete instantaneous...
Neural networks can be used to identify and remove noise from noisy speech spectrum (denoisisng autoencoders, DAEs). The DAEs are typically implemented using the fully-connected feed-forward topology. Usually one of the following possibilities is used as DA target: 1) Ideal frequency ratio mask, which is applied to noisy spectrum to estimate the clean speech spectrum (masking) or 2) Clean speech spectrum...
Monaural speech enhancement is a key yet challenging problem in speech area, which is always used as a pre-processing step of robust speech processing. Deep learning has proved to be very successful for solving this issue. In this paper, a new approach for enhancing the noisy speech in a single channel recording is presented. We propose a modified ideal ratio mask (IRM) which calculated by normalized...
In this work, we present a low-complexity single-ended objective intelligibility measure for noisy speech based on statistics computed from auditory modulation features. The proposed measure is obtained in two steps. First, we compute several statistics of auditory representation of corrupted speech. Next, a support vector regressor (SVR) is used to map these statistics to an overall intelligibility...
This paper compares the use of signal to noise ratio (SNR)-dependent and SNR-independent mixtures of probabilistic linear discriminant analysis (PLDA) versus conventional PLDA, under multi-noise and multi-SNR conditions for a small-set speaker verification system. Results indicate that conventional PLDA is more robust under multi-SNR conditions. The effect of the testing speech length is also examined...
A novel waveforms classification method based on convolutional neural networks (CNN) is proposed in this paper. Firstly, convolution and pooling operations are cross used for generating deep features, and then fully connected to the output layer for classification. Different from other traditional approaches which need human-designed features, CNN can discover and extract the suitable internal structure...
Audio-visual speech recognition is a promising approach to tackling the problem of reduced recognition rates under adverse acoustic conditions. However, finding an optimal mechanism for combining multi-modal information remains a challenging task. Various methods are applicable for integrating acoustic and visual information in Gaussian-mixture-model-based speech recognition, e.g., via dynamic stream...
Recent work on developing training methods for reduced precision Deep Convolutional Networks show that these networks can perform with similar accuracy to full precision networks when tested on a classification task. Reduced precision networks decrease the demand on the memory and computational power capabilities of the computing platform. This paper investigates the impact of reduced precision deep...
A cost effective approach to remote monitoring of protected areas such as marine reserves and restricted naval waters is to use passive sonar to detect, classify, localize, and track marine vessel activity (including small boats and autonomous underwater vehicles). Cepstral analysis of underwater acoustic data enables the time delay between the direct path arrival and the first multipath arrival to...
DNN based acoustic models require a large amount of training data. Parametric data augmentation techniques such as adding noise, reverberation, or changing the speech rate, are often employed to boost the dataset size and the ASR performance. The choice of augmentation techniques and the associated parameters has been handled heuristically so far. In this work we propose an algorithm to automatically...
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.