In this paper we propose a new source localization method using underwater ambient noise modeling based on heteroscedasticity tune series in array signal processing for a passive SONAR. In this application, measuremen...
详细信息
In the past years, modeling and simulation of hybrid dynamic systems (HDS) have attracted much attention. However, since simultaneously dealing with the discrete and continuous variables is very difficult, most of the...
详细信息
Unseen handset mismatch is the major source of performance degradation for speaker recognition in telecommunication environment since handset distortions are tightly coupled with speaker characteristics. In this paper...
详细信息
Unseen handset mismatch is the major source of performance degradation for speaker recognition in telecommunication environment since handset distortions are tightly coupled with speaker characteristics. In this paper, a soft-decision unseen handset characteristics estimation method based on a priori knowledge interpolation is proposed to decouple the characteristics of the unseen handset and speaker for robust speaker recognition. Experimental results on HTIMIT database showed that the proposed method improved the speaker recognition rate for both seen and unseen handsets.
The sub-Nyquist nonuniform sampling (SNNS) scheme and the corresponding perfect reconstruction formula are addressed. Also, a condition to enable the perfect reconstruction of the continuous-time signal from its nonun...
详细信息
Most speaker recognition systems utilize only low-level short-term spectral features and ignore high-level long-term information, such as prosody and speaking style. This paper presents a novel eigen-prosody analysis ...
详细信息
Most speaker recognition systems utilize only low-level short-term spectral features and ignore high-level long-term information, such as prosody and speaking style. This paper presents a novel eigen-prosody analysis (EPA) approach to capture long-term prosodic information of a speaker for robust speaker recognition under mismatch environment. It converts the prosodic feature contours of a speaker's speech into sequences of prosody symbols, and then transforms the speaker recognition problem into a full text document retrieval-similar task. Experimental results on the well-known HTIMIT database have shown that, even only few training/test data is available, a remarkable improvement, about 28.7% relative error rate reduction comparing with the GMM/cepstral mean subtraction (CMS) baseline, could be achieved.
Parameter estimation of an autoregressive moving average (ARMA) model is discussed in this paper by using bounding approach Bounds on the model structure error are assumed unknown, or known but conservative To reduce ...
详细信息
The paper proposes an approach to design a structure for control of integrated wastewater treatment plant-sewer system under full range of disturbance inputs. The control activities are hierarchically structured into ...
详细信息
Difficulties occui when one universal control strategy attempts controlling a plant that is under wide range of operating conditions In order to best adopt the control strategy to existing conditions three operational...
详细信息
control of integrated wastewater treatment plant-sewer systems under full range of disturbance inputs enforces employing advanced optimising control algorithms. The control activities are hierarchically structured int...
详细信息
暂无评论