A new classification feature extraction method for Chinese-Korean spoken language identification was proposed in this paper. Firstly, speech signal was divided into frame serial and the number of frames was counted. F...
A new classification feature extraction method for Chinese-Korean spoken language identification was proposed in this paper. Firstly, speech signal was divided into frame serial and the number of frames was counted. Furthermore, the ratio between short-time zero-crossing rate and short-time energy, i.e. short-time-frequency-energy-ratio (STFER), was computed, and the mean STFER per frame was treated as the classification feature to implement Chinese-Korean spoken language identification. Finally, the classification threshold was determined using information gain. Experimental results show that the proposed method is simpler than MFCC feature parameters and has better ability to identify spoken language with lower complexity, can be adopted in preprocessing procedure of language recognition.
This paper proposes a new method for estimating the direction-of-arrival (DOA) of wideband signal, which employs particle filters to track array manifold at different frequency bands. Compared with the coherent signal...
详细信息
This paper proposes a new method for estimating the direction-of-arrival (DOA) of wideband signal, which employs particle filters to track array manifold at different frequency bands. Compared with the coherent signal-subspace method (CSM), the proposed method utilizes the current observed data and does not require the estimated covariance matrix, thus it performs better while considering a small sample set. In the meantime, this method does not require the preliminary DOA estimates. Moreover, the proposed method can localize completely correlated sources as it is based on the idea of maximum likelihood. Simulation results show that the performance of the propose method is better than CSM when the sample set is small, the signal to noise ratio (SNR) is low and the signal sources are correlated.
Keyword spotting (KWS) refers to detection of a limited number of given keywords in speech utterances. In this paper, we evaluate a robust keyword spotting system based on hidden markov models for speaker independent ...
详细信息
Keyword spotting (KWS) refers to detection of a limited number of given keywords in speech utterances. In this paper, we evaluate a robust keyword spotting system based on hidden markov models for speaker independent Persian conversational telephone speech. Performance of base line keyword spotter is improved by means of normalizing features using cepstral mean and variance normalization (CMVN) and cepstral gain normalization (CGN). And better performance is gained by applying auto-regressive moving average (ARMA) filter on normalized features. Experimental results show that although all these methods improve keyword spotting performance, CMVN and ARMA (MVA) processing of PLP features works much better on our Persian conversational telephone speech database and 41% improvement to baseline system is achieved at false alarm (FA) rate equal to 8.6 FA/KW/Hour.
When the cone-shaped target is flying in exo-atmosphere, the micro-motion of the target belongs to a precession and that of the decoy belongs to a spin or a wobble. Because they are different in micro-motion, the char...
详细信息
When the cone-shaped target is flying in exo-atmosphere, the micro-motion of the target belongs to a precession and that of the decoy belongs to a spin or a wobble. Because they are different in micro-motion, the characteristic spectrum is extracted as a recognition feature. The paper models multi-section radar signals and analyzes the micro-Doppler signature of the warhead and the decoy. Although the micro-Doppler Spectrum of precession targets, wobble targets and spin targets is approximated as a line-Spectrum, but there is a significant difference. Based on the harmonic model, eigenvalue decomposition is applied to compute the eigenvalue as the recognition feature. Simulation proves that the method is effective.
Prior work about uncertainty visualization has been primarily focused on spatio-temporal or univariate data. Little research has been reported on exploring uncertainty of multidimensional data. Therefore, improved vis...
详细信息
Prior work about uncertainty visualization has been primarily focused on spatio-temporal or univariate data. Little research has been reported on exploring uncertainty of multidimensional data. Therefore, improved visualizations applying to parallel coordinate and star glyph will be discussed and utilized to visualize multidimensional uncertainty. Firstly, parallel coordinate will be modified through imposing visual variables and expanding traditional two-dimensional visualization to three-dimensional way. Then the concept of multi-view visualizationwill be put forward,multidimensional uncertainty of data will be mapped by interactive integration of the visual representations of Parallel Coordinate and Star Glyph, which utilizes the advantages of both representations to offset the disadvantages they have separately to overcome the shortcoming that traditional parallel coordinate cannot map order of data and the problem of overlapping polylines. Meanwhile, four HCI technologies such as brushing, Linking, Zooming in/out, Hiding are imposed to the improved visualizations to help users to focus on what they find interesting and details of corresponding data with different uncertainty intervals. Eventually, MFC and OPENGL technology will be combined to construct an experimental platform to validate our proposed new ideas.
An improvement is made to traditional particle system technology in rainfall simulation. In order to improve the authenticity and flexibility of rainfall simulation and speed up the rendering speed, the particle rotat...
详细信息
An improvement is made to traditional particle system technology in rainfall simulation. In order to improve the authenticity and flexibility of rainfall simulation and speed up the rendering speed, the particle rotation, particle dynamic texture, dynamic color etc. are introduced. The structure of particles is simplified. Meanwhile, a funnel model is adopted to adapt to the characteristics of a flight simulator. Experiment results show that the proposed method has gotten realistic visual effect and real-time speed, and is especially suitable for large flight simulator scene.
An adaptive antenna array system adjusts the main lobe of radiation pattern in the direction of desired signal and points the nulls in the direction of undesired signals or interferers. The essential goal of beamformi...
详细信息
An adaptive antenna array system adjusts the main lobe of radiation pattern in the direction of desired signal and points the nulls in the direction of undesired signals or interferers. The essential goal of beamforming is to reduce the complexity of weighting process and to decrease the time needed for adjusting the antenna radiation pattern. In this article a new adaptive weighting algorithm is proposed for both least mean squares (LMS) and constant modulus (CM) algorithms. It is appropriate and applicable for antenna array systems with moving targets and also mobile applications as well as sensor networks. By predicting the relative velocity of source, the next location of the source will be estimated and the array weights will be determined using LMS or CM algorithm before arriving to the new point. For the next time associated to the new sampling point, evaluated weights will be used. Furthermore, by updating these weights between two consecutive times the effects of error propagation will be eliminated. Therefore, in addition to reduction in computational complexity at the time of weight allocation, relatively accurate weight allocation can be obtained. Simulation results of this investigation show that the angular error related to both LMS-based and CM-based algorithms is less than the conventional LMS and CM algorithms at different signal to noise ratios (SNRs). On the other hand, due to considering off-line process, online computational complexity of new algorithms is slightly low with respect to previous ones.
With the rapid increase of websites and internet users, the traditional search engine will face great challenge in the real-time search, response speed and the storage of mass pages. However, the search engine deploye...
详细信息
With the rapid increase of websites and internet users, the traditional search engine will face great challenge in the real-time search, response speed and the storage of mass pages. However, the search engine deployed in the cloud can solve these shortcomings due to cloud computing with two major advantages in mass data processing and mass data storage. By analyzing the open-source cloud computing system Hadoop, a cloud platform search engine model is constructed and the core algorithm of search engine is optimized to improve the overall performance of search engine.
Machine type communications have emerged with new types of applications and revenue sources both for network operators and cellular/network equipment companies. This new kind of service may increase significantly the ...
详细信息
Machine type communications have emerged with new types of applications and revenue sources both for network operators and cellular/network equipment companies. This new kind of service may increase significantly the number of devices accessing the network in the next few years, and could have some impacts over the current services, namely normal voice and data services. One important concern is related to effects of extreme cases where MTC devices may act in a synchronized way. In GSM networks, the signaling capacity may be temporarily blocked, limiting the access of normal services for some seconds, or even minutes. This paper proposes one solution for overload problem caused by MTC device synchronization using the Orthogonal sub- channels technique (OSC). Statistical analysis over the effects of synchronized MTC devices are used to provide an overview on the achievable access procedure delay reduction when using this technique. The proposed technique has proven to decrease the average delay of normal services by 70% and to reduce by 50% the overload period of the signaling channels.
Increased attention has been drawn to machine type communication (MTC) lately, which represents important extension for user functionality in today's technologies, as well as an important potential for marketing e...
详细信息
Increased attention has been drawn to machine type communication (MTC) lately, which represents important extension for user functionality in today's technologies, as well as an important potential for marketing expansion. GERAN studies over MTC has mainly focused on applications requiring low throughput and wide coverage such as smart meter, which could cause some impacts over normal data users if operating in a synchronous manner. This paper proposes a new methodology for studying the impact on signaling channels when mixture of synchronous and asynchronous traffic is present in the network. This is based on statistical analysis, considering signaling accessing attempts as driven by a Poisson process. In this approach successive random access attempts by the mobile stations are considered as well as the response on the network side. First implementation is held for GSM/GPRS network, although generalization of the method for other technologies is possible. The simulated results show potential problems to be solved when a large number of synchronized users is present. Additionally, an analysis on the effects of the different levels of synchronization and the addition of extra signaling channels is included. Results also point out possible development paths that could be taken when designing new features to make networks more robust to synchronized traffic.
暂无评论