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.
The Smith-Waterman algorithm, which produces the optimal local alignment between pairwise sequences, is universally used as a key component in bioinformatics fields. It is more sensitive than heuristic approaches, but also more time-consuming. To speed up the algorithm, Single-Instruction Multiple-Data (SIMD) instructions have been used to parallelize the algorithm by leveraging data parallel strategy...
Attention mechanism advances the neural machine translation (NMT) by reducing the confusion introduced by irrelevant words in long sentences. However, the confusion caused by ambiguous words hasn't been handled yet and it may be a bottleneck for the NMT model. This paper validates the hypothesis and proposes a simple and flexible framework, which enables the NMT model to only focus on the relevant...
In automatic speech recognition (ASR), connectionist temporal classification (CTC) is regarded as a method to achieve end-to-end system. Actually, not only characters (Chars) but also context independent phonemes (CI-Phns) or context dependent phoneme (CD-Phns) can be used as output units of CTC-trained neural network. The contribution of this paper mainly lies in three aspects: First, we trained...
Text generation is a typical nature language processing task, and is the basis of machine translation and question answering. Deep learning techniques can get good performance on this task under the condition that huge number of parameters and mass of data are available for training. However, human beings do not learn in this way. People combine knowledge learned before and something new with only...
Human beings receive stimulations in primary sensory cortex and transfer them to higher brain regions automatically. What happened in this procedure? In this paper, we will focus on one of these regions (hippocampus) and try to simulate its working procedure by building an HMSNN (Hippocampus inspired Memory Spiking Neural Network) model. Dentate Gyrus (DG) and Cornu Ammonis area 3 (CA3) are the main...
Word segmentation is the first step in Chinese natural language processing, and the error caused by word segmentation can be transmitted to the whole system. In order to reduce the impact of word segmentation and improve the overall performance of Chinese short text classification system, we propose a hybrid model of character-level and word-level features based on recurrent neural network (RNN) with...
Job scheduling is a necessary prerequisite for performance optimization and resource management in the cloud computing system. Focusing on accurate scaled cloud computing environment and efficient job scheduling under Virtual Machine (VM) resource and Server Level Agreement (SLA) constraints, we introduce the architecture of cloud computing platform and optimization job scheduling scheme in this study...
Reinforcement learning is an area of machine learning inspired by behaviorist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. Recently reinforcement learning has been given abroad attention, but when it is applied to solve problems with large-scale discrete or contiguous state space environments, the results...
Speech activity detection (SAD) is the key preprocess of speech application. This paper proposed a subspace Gaussian mixture model (SGMM) and phoneme combination based SAD algorithm. This algorithm is efficient, small and can utilize speech recognition corpus directly. Results indicate that, compared with the baseline, our proposed method results in an absolute improvement of 4.9% frame error rate...
Process algebra have been effectively exploited for modeling and verifying functional aspects of services composition, but non-functional aspects have not been given enough care due to process algebra lacking of capability of modeling them. In this paper, we propose a novel process algebra called PTPA that incorporates price and cost. We present syntax and semantics of PTPA. And an algorithm is proposed...
Sentiment analysis has now become a popular research problem to tackle in NLP field. However, there are very few researches conducted on sentiment analysis for Chinese. Progress is held back due to lack of large and labelled corpus and powerful models. To remedy this deficiency, we build a Chinese Sentiment Treebank over social data. It concludes 13550 labeled sentences which are from movie reviews...
In the task of mispronunciation detection, the cross-speaker degradation and some other confusing nuisances are the challenging problems demanding prompt solution. In this paper, we will attempt to remove the non-pronunciation variations in the GLDS-SVM expansion space by using nuisance attribute projection strategy, in order to increase the separating capacity between different phoneme instances...
This paper presented a fast algorithm which could measure similarity between two meshes interactively. The algorithm was based on CUDA (Compute Unified Device Architecture) technology. In order to fully utilize the computing power of GPU, we developed parallel method to construct uniform grid for fast space indexing of triangles. Special data structure was designed on device end to overcome the disadvantage...
This paper presents a formal imperative calculus to formalize the semantics of class-based object-oriented programming languages. The tractability of this approach is demonstrated by our formalization of a core subset of the Java programming language called Cool: Core Object-Oriented Language. Cool is relatively small but retains many of modern class-based object-oriented languages' key features,...
Experimental teaching is widely applied in the fields of natural science, engineering, ecology and social science etc. It is also witnessed the increasingly penetrating into business related teaching and training. In particular, simulation based experiment has got immense attention in many management and economics schools of the universities. Simulation based experimental teaching helps the students...
Application of multimedia technology in teaching and knowledge transfer is booming. Pilot experiment uses interactive computer-based gaming in which people play a role in the system being modeled. The behavior of subjects can then be directly compared against the behavior produced by the assumed decision rules of the model. Interactive Learning Environment (ILE) methodology provides a mimic real system...
Mispronunciation detection is an important component in computer assisted language learning (CALL) system. In this work, we introduce an efficient GLDS-SVM based detection method, which is successfully used in language and speaker identification systems, and combine it with traditional methods. The main ideas include: extended MFCC features with normalized formant trajectory information, and then...
Monaural speech segregation is a very challenging problem which has been studied by many researchers. In this paper, we focus on voiced speech segregation. Different strategies are used to segregate resolved and unresolved harmonics respectively. For resolved harmonics, "harmonicity" principle and a novel mechanism based on "minimum amplitude" principle are employed. Amplitude...
In this paper, we introduce a multipitch detection algorithm which is based on weighted summary correlogram. The weight is described as a conditional probability which models the relationship between fundamental frequency (FO) of periodic sound and response frequency of its dominated channels. Modified by this weight, SACF obtains more robustness to noise and to sub-harmonic error. The proposed algorithm...
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.