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 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...
To improve the performance of noisy automatic speech recognition (ASR), it is effective to prepare multiple ASR systems that can address the large varieties of noise. However, the optimal ASR system is different for each environment and mismatches between training and testing degrade ASR performance. In this situation, the overall system combination of multiple systems is effective; however, the computational...
Speech enhancement plays an important role in robust speech processing. Deep learning has become a new trend towards solving speech enhancement problems. The input feature is a key aspect of deep learning, which effect the enhancement performance. In this paper, we explore a new feature which extract through the minimum mean square error (MMSE) estimator pretreatment. Incorporating the MMSE pretreatment...
Building Automatic Speech Recognition (ASR) needs acoustic model, language model and dictionary for intended language, which is also applied for Indonesian ASR. In this paper, Indonesian ASR was built using CMUSphinx toolkit (a Hidden Markov Model based ASR tool) with limited dataset. We use digit corpus and own made language model to trained with the limited dataset. We also investigated the implementation...
Automatic modulation classification (AMC) plays a key role in cognitive radar, cognitive radio and some other civilian and military fields to identify the type of modulation. In this paper, a deep learning based modulation classification method is developed for discriminating digital modulated signals. This proposed method uses a stacked sparse auto-encoders to extract features from ambiguity function...
Classification performances of the supervised machine learning techniques such as support vector machines, neural networks and logistic regression are compared for modulation recognition purposes. The simple and robust features are used to distinguish continuous-phase FSK from QAM-PSK signals. Signals having root-raised-cosine shaped pulses are simulated in extreme noisy conditions having joint impurities...
We introduce learned attention models into the radio machine learning domain for the task of modulation recognition by leveraging spatial transformer networks and introducing new radio domain appropriate transformations. This attention model allows the network to learn a localization network capable of synchronizing and normalizing a radio signal blindly with zero knowledge of the signal's structure...
Beamforming (BF) protocols introduced in IEEE 802.11ad and IEEE 802.15.3c for 60 GHz millimeter-wave (mmwave) communications perform exhaustive sector/beam search to setup a beamformed link between stations/devices. In this paper, we propose two BF methods, Binary Search Beamforming (BSB) and Linear Search Beamforming (LSB), to improve the BF setup time of adopted algorithms in IEEE 802.11ad and IEEE...
In millimeter wave (mmWave) systems adopting large number of antennas at both the transmitter and the receiver, channel estimation is challenging due to the large number of antennas and low signal-to-noise ratio (SNR) before beamforming. Due to the sparse nature of mmWave channels, the channel estimation can be solved by beam search. While conventional beam search schemes rely on exhaustive training,...
This paper classifies noisy English Alphabets with the help of Artificial Neural Network. Here a supervised single layer perceptron learning algorithm for the classification of noisy English alphabets has been proposed. The presented algorithm requires very few number of input neurons for training. The algorithm is capable of classification of English alphabets for different scenario of noise. Simulation...
In this paper, we propose a comparison method of training symbol (or preamble) and Cyclic Prefix (CP) to improved the frequency synchronization in orthogonal frequency division multiplexing (OFDM). The problems that arise in OFDM system is the time-shift and frequency mismatch between the oscillators in the transmitter and the receiver. It is known as a Carrier Frequency Offset (CFO) problem. By exploring...
For wireless remote access security, forensics, electronic commerce and surveillance applications, there is a growing need for biometric speaker identification systems to be robust to noise. This paper examines the robustness issue for the case of additive white noise at signal to noise ratios ranging from 0 to 30 dB. A Gaussian mixture model classifier based on adaptation of a universal background...
This paper proposes a novel regression approach to binaural speech segregation based on deep neural network (DNN). In contrast to the conventional ideal binary mask (IBM) method using DNN with the interaural time difference (ITD) and in-teraural level difference (ILD) as the auditory features, the log-power spectra (LPS) features of target speech are directly predicted via a regression DNN model by...
The reverberant speech segregation is a basic problem in speech enhancement and automatic speech recognition. Based on the deep neural networks (DNN), a novel binaural speech segregation method is proposed. The binaural feature is extracted and used as the cue to train a DNN with a ideal parameter mask. The trained DNN is used to distinguish the target speech and noise, and output the estimated parameter...
A well-known problem with modern anti-submarine warfare sonars with narrow beamwidths and wide frequency bandwidths, is the frequent occurence of false alarms, particularly in littoral environments. This increases the workload of sonar operators and also reduces the usefulness of automatic systems such as autonomous underwater vehicles, since their limited communication abilities hinder them from...
Various ideal masks have been used as the training targets for supervised speech separation. While different choices often lead to different results, the reason remains unclear. In this paper, an oracle method is applied to investigate the properties of the ideal masks including the ideal binary mask (IBM), the ideal ratio mask (IRM), the phase sensitive mask (PSM) and the complex ideal ratio maks...
In this paper, a quasi-Newton method for semi-blind estimation is derived for channel estimation in uplink cloud radio access networks (C-RANs). Different from traditional pilot-aided estimation, semi-blind estimation utilizes the unknown data symbols in addition to the known pilot symbols to estimate the channel. An initial channel state information (CSI) obtained by least-squared (LS) estimation...
Monaural speech enhancement is a key yet challenging problem for many important real world applications. Recently, deep neural networks(DNNs)-based speech enhancement methods, which extract useful feature from complex feature, have demonstrated remarkable performance improvement. In this paper, we present a novel DNN architecture for monaural speech enhancement. Taking into account the masking properties...
The adoption of clean, renewable energy has brought to the forefront an increase in the studies and research around their reliable and efficient implementation. The increasing demand of wind-turbine generated power has led to the construction of larger turbines which require higher reliability guarantees in order to operate with reduced down-times and moderate repair costs. The use of advanced techniques...
The spectrum sensing function allows a cognitive radio to determine the absence/presence of primary users' (PUs) signals in a frequency band of interest. These signals might exhibit very low-power at cognitive (or secondary) users' receivers. Thus requiring detection algorithms that work well in the very low signal-to-noise ratio (SNR) region. It is known that secondary users (SUs) can improve its...
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.