Comparing ANN and GMM in a voice conversion framework

In this paper, we present a comparative analysis of artificial neural networks (ANNs) and Gaussian mixture models (GMMs) for design of voice conversion system using line spectral frequencies (LSFs) as feature vectors. Both the ANN and GMM based models are explored to capture nonlinear mapping functions for modifying the vocal tract characteristics of a source speaker according to a desired target speaker. The LSFs are used to represent the vocal tract transfer function of a particular speaker. Mapping of the intonation patterns (pitch contour) is carried out using a codebook based model at segmental level. The energy profile of the signal is modified using a fixed scaling factor defined between the source and target speakers at the segmental level. Two different methods for residual modification such as residual copying and residual selection methods are used to generate the target residual signal. The performance of ANN and GMM based voice conversion (VC) system are conducted using subjective and objective measures. The results indicate that the proposed ANN-based model using LSFs feature set may be used as an alternative to state-of-the-art GMM-based models used to design a voice conversion system.     

Estimation and forecasting with logarithmic autoregressive conditional duration models: A comparative study with an application

This paper presents a semi-parametric method of parameter estimation for the class of logarithmic ACD (Log-ACD) models using the theory of estimating functions (EF). A number of theoretical results related to the corresponding EF estimators are derived. A simulation study is conducted to compare the performance of the proposed EF estimates with corresponding ML (maximum likelihood) and QML (quasi maximum likelihood) estimates. It is argued that the EF estimates are relatively easier to evaluate and have sampling properties comparable with those of ML and QML methods. Furthermore, the suggested EF estimates can be obtained without any knowledge of the distribution of errors is known. We apply all these suggested methodology for a real financial duration dataset. Our results show that Log-ACD (1, 1) fits the data well giving relatively smaller variation in forecast errors than in Linear ACD (1, 1) regardless of the method of estimation. In addition, the Diebold–Mariano (DM) and superior predictive ability (SPA) tests have been applied to confirm the performance of the suggested methodology. It is shown that the new method is slightly better than traditional methods in practice in terms of computation; however, there is no significant difference in forecasting ability for all models and methods.     

Signal transformation and interpolation based on modified DCT synthesis

This paper proposes a novel signal transformation and interpolation approach based on the modification of DCT (Discrete Cosine Transform). The proposed algorithm can be applied to any periodic or quasi periodic waveform for time scale and/or pitch modification purposes in addition to signal reconstruction, compression, coding and packet lost concealment. The proposed algorithm has two advantages:

• (i) 

  Since DCT does not have the explicit phase information, one does not need the cubic spline interpolation of the phase component of the sinusoidal model.

• (ii) 

  The parameters to be interpolated can be reduced because of the energy packing efficiency of the DCT. This is particularly important if signal synthesis is carried out on a remote location from the transmitted parameters.

The results are presented on periodic waveforms and on speech signal in order to appreciate the fidelity of the proposed algorithm. In addition, the proposed method is compared with TD-PSOLA, sinusoidal model and phase vocoder algorithms. The results are presented in objective PESQ scores for time scale modification and output files are provided as supplementary material,¹ for subjective evaluation, for packet lost concealment. Results prove that the proposed modification of the DCT synthesis provides a favorable algorithm for specialists working in the signal processing area.     

Audio indexing: primary components retrieval

This work addresses the soundtrack indexing of multimedia documents. Our purpose is to detect and locate sound unity to structure the audio dataflow in program broadcasts (reports). We present two audio classification tools that we have developed. The first one, a speech music classification tool, is based on three original features: entropy modulation, stationary segment duration (with a Forward–Backward Divergence algorithm) and number of segments. They are merged with the classical 4 Hz modulation energy. It is divided into two classifications (speech/non-speech and music/non-music) and provides more than 90% of accuracy for speech detection and 89% for music detection. The other system, a jingle identification tool, uses an Euclidean distance in the spectral domain to index the audio data flow. Results show that is efficient: among 132 jingles to recognize, we have detected 130. Systems are tested on TV and radio corpora (more than 10 h). They are simple, robust and can be improved on every corpus without training or adaptation.

基于LD预测的车载自组网下一跳选择算法

在高速移动环境中,车载自组网的下一跳节点选择算法存在高丢包率的问题。为此,在贪婪算法的基础上,通过预测车辆节点的链路持续时间(LD)和数据发送时延,提出一种改进的下一跳节点选择算法。其中,转发节点根据邻居节点和自身的相对速度,预测该节点和当前节点间的链路持续时间,选择其值不小于待发数据的发送时延的邻居节点作为下一跳节点。仿真实验结果表明,改进算法可以明显降低贪婪算法的丢包率。     

项目活动时间估算的适用性研究

在项目活动时间三次估算公式的基础上,根据活动时间分布,试图减少一个极端值的估算,得出两次估算方法,以此降低时间估算中的主观性和时间估算的次数,并对两种方法推导出项目活动时间均值和方差的计算路径,同时构造了样本假设检验的方法,在试验的基础上对两种估算进行比较,从而判断和改善项目活动时间估算的适用性.最后通过实证得出当偏差系数小于-0.4或大于0.2时,活动时间估算采用三次比较适宜;当偏差系数位于二者之间时,采用二次估算比较适宜.     

混合系统的建模设计与仿真综述

混合系统是一类既包含连续动态行为又包含离散动态行为的系统,这类系统在实际应用中显得越来越重要,对这类系统需要探索新的模型和研究方法。该文在概述混合系统概念、特点以及发展近况的基础上,主要综述了近年来混合系统研究中的一些重要问题,指出现有各种方法的优缺点,并指出了今后的研究方向。该文首先介绍了混合系统研究中多种常见的建模方法,如混合自动机、Petri网和时段演算,然后重点讨论了混合系统一些重要性质,主要集中在对系统稳定性、可达性、可观性的分析方法上,以及混合系统的多种设计方法,并且对这些方法进行了初步评价,最后介绍了混合系统研究中一些常用的仿真工具。     

厄瓜多尔流域综合规划适宜生态流量研究

在厄瓜多尔水资源管理工作中,生态流量管控尚未被应用于具体实践。为此,参考中国的水资源保护管理经验,将生态流量管控作为水资源保护的重要手段引入厄瓜多尔流域综合规划中。在对生态流量发展历史、计算方法和应用情况进行系统总结和分析的基础上,根据厄瓜多尔基础资料现状情况及管理要求,在制定水资源保护规划时,确定了212个生态流量控制断面,并应用Tennant法和流量历时曲线法计算了各控制断面的生态流量。     

Using duration models to reduce fragmentation in audio segmentation

We investigate explicit segment duration models in addressing the problem of fragmentation in musical audio segmentation. The resulting probabilistic models are optimised using Markov Chain Monte Carlo methods; in particular, we introduce a modification to Wolff’s algorithm to make it applicable to a segment classification model with an arbitrary duration prior. We apply this to a collection of pop songs, and show experimentally that the generated segmentations suffer much less from fragmentation than those produced by segmentation algorithms based on clustering, and are closer to an expert listener’s annotations, as evaluated by two different performance measures. Editor: Gerhard Widmer     

优先级顶协议的形式化验证

优先级顶协议是一种优先级驱动的抢占式调度协议,它具有无死锁和单阻塞的性质.Dang Van Hung 和Philip Chan在文献[6]中形式地规范和验证了这两个性质.但他们没有对状态函数HiPripcp明确定义,这使得验证的细节较难理解.为了解决这个问题,提出了一种新的方法来验证优先级顶协议单阻塞的性质.通过时段演算的方法,对优先级顶协议进行了规范,并给出了状态函数HiPripcp的明确定义.根据优先级顶协议的规范,形式地验证了该协议的单阻塞性质.采用的验证方法更少地依赖于HiPripcp,这使得验证的细节更易于理解.此外,提出的验证方法可被应用于实时数据库系统中类似协议的形式化验证.