Adaptability and controllability are the major advantages of statistical parametric speech synthesis (SPSS) over unit-selection synthesis. Recently, deep neural networks (DNNs) have significantly improved the performa...
详细信息
ISBN:
(纸本)9781509024018
Adaptability and controllability are the major advantages of statistical parametric speech synthesis (SPSS) over unit-selection synthesis. Recently, deep neural networks (DNNs) have significantly improved the performance of SPSS. However, current studies are mainly focusing on the training of speaker-dependent DNNs, which generally requires a significant amount of data from a single speaker. In this work, we perform a systematic analysis of the training of multi-speaker average voice model (AVM), which is the foundation of adaptability and controllability of a DNN-based speech synthesis system. Specifically, we employ the i-vector framework to factorise the speaker specific information, which allows a variety of speakers to share all the hidden layers. And the speaker identity vector is augmented with linguistic features in the DNN input. We systematically analyse the impact of the implementations of ivectors and speaker normalisation.
The paper proposes a new network intrusion detection system based on fuzzy neural network by redesigning the intrusion detection system's architecture and arithmetic. In order to overcome the difficulty of specify...
详细信息
ISBN:
(纸本)7900719229
The paper proposes a new network intrusion detection system based on fuzzy neural network by redesigning the intrusion detection system's architecture and arithmetic. In order to overcome the difficulty of specifying the membership function of rules depending on experiences of experts in multi-dimension space.,neural network is introduced to distinguish non-linearly input/output characteristics of complex system and to generate rule sets and membership functions automatically. The new architecture adopts the network processor to collect and analyse the data in the low layer of network.,and to establish a prototype system. This system demonstrated in this experiment appears to be better intrusion detection ability, moreover, which is able to detect unknown attack and plays down false alarms.
We present a novel method for 3D face recognition, in which the 3D facial surface is first mapped into a 2D domain with specified resolution through a global optimization by constrained conformal geometric maps. The I...
详细信息
ISBN:
(纸本)9781424442959
We present a novel method for 3D face recognition, in which the 3D facial surface is first mapped into a 2D domain with specified resolution through a global optimization by constrained conformal geometric maps. The Intrinsic Shape Description Map (ISDM) is then constructed through a modeling technique capable to express geometric and appearance information of the 3D face. Hence the 3D surface matching problem can be simplified to a 2D image matching problem, which greatly reduces the computational complexity. Finally, the Intrinsic Shape Description Feature (ISDF) of ISDM and the discrimination analysis can be calculated. Experimental results implemented on GavabDB demonstrate that our proposed method significantly outperforms the existing methods with respect to pose variation.
This study aims to address the complexity of predicting RNA-small molecule binding sites to explore the potential value in the field of RNA drug targets. To address this challenge, we propose the MultiModRLBP method, ...
详细信息
The user often retrieves few anticipated results when searching information in Internet via generalized search engine due that the web pages also exist the synonymous and ambiguous characteristic. How to classify the ...
详细信息
The user often retrieves few anticipated results when searching information in Internet via generalized search engine due that the web pages also exist the synonymous and ambiguous characteristic. How to classify the webpage is the key point to construct vertical search engine, which is known as solution for the problems. This paper proposes a conceptual framework based on Learning Vector Quantization (LVQ) network and Ontology to automatic classification for the webpage from agricultural website. System test shows that the framework can automatically classify Chinese agricultural products web pages and perfectly resolve the synonymous problem.
A fuzzy clustering algorithm for intrusion detection based on heterogeneous attributes is proposed in this paper. Firstly, the algorithm modifies the comparability measurement for the categorical attributes according ...
详细信息
The tradition standby mechanism can't carry out the dynamic Disaster Recovery of database between distributed isomeric storage systems, accordingly, research the method of allopatric isomeric backup based on grid ...
The tradition standby mechanism can't carry out the dynamic Disaster Recovery of database between distributed isomeric storage systems, accordingly, research the method of allopatric isomeric backup based on grid calculation is an important research subject. In this paper, some technique and strategy of allopatric isomeric backup in grid calculation environment are researched by comparing and analyzing the existing technique of database allopatric backup, a remote-data copy method is presented, a remote-data disaster dump system and a allopatric isomeric data Disaster Recovery tool are designed and implemented based on interlayer.
Optical scanning holography (OSH) is a variant of two-pupil heterodyning image processing. We investigate the use of one pupil as a delta function and the other being an annulus as an extended application of OSH. ...
详细信息
In the problem of domain transfer learning, we learn a model for the prediction in a target domain from the data of both some source domains and the target domain, where the target domain is in lack of labels while th...
详细信息
Recently, Authentication protocol has been recognized as an important factor for grid computing security. This paper described a new simple and efficient Grid authentication system providing user anonymity. Our system...
Recently, Authentication protocol has been recognized as an important factor for grid computing security. This paper described a new simple and efficient Grid authentication system providing user anonymity. Our system is based on hash function, and mobile users only do symmetric encryption and decryption. In our system, it takes only one round of messages exchange between the mobile user and the visited network, and one round of message exchange between the visited network and the corresponding home network. The proposed architecture possesses several desirable emerging properties that enable it to provide an improved level of security for grid computing systems..
暂无评论