This paper describes techniques for segmentation of conversational speech based on speaker identity. Speaker seg-mentation is performed using Viterbi decoding on a hidden Markov model network consisting of interconnected speaker sub-networks. Speaker sub-networks are initialized using Baum-Welch training on data labeled by speaker, and are iteratively retrained based on the previous segmentatio...

We re-examine Sephton and Larsen's (1991) conclusion that cointegration-based tests for market efficiency suffer from temporal instability. We improve upon their research by i) including a drift term in the vector error correction model (VECM) in the Johansen procedure, ii) correcting the likelihood ratio test statistic for finitesample bias, and iii) fitting the model over longer data sets. We...

In this paper, the second of a series of two, we continue the study of higher index theory for expanders. We prove that if a sequence of graphs has girth tending to infinity, then the maximal coarse Baum-Connes assembly map is an isomorphism for the associated metric space X. As discussed in the first paper in this series, this has applications to the Baum-Connes conjecture for ‘Gromov monster’...

Empirical evidence obtained from data covering Eurozone countries, other industrialized countries, and newly industrialized countries (NICs) over 1980– 2006 shows that exchange rate uncertainty has a consistent positive and significant effect on the volatility of bilateral trade flows. A one standard deviation increase in exchange rate uncertainty leads to an eight per cent increase in trade vo...

The canonical trace on the reduced C∗-algebra of a discrete group gives rise to a homomorphism from the K-theory of this C∗-algebra to the real numbers. This paper addresses the range of this homomorphism. For torsion free groups, the Baum-Connes conjecture and Atiyah’s L-index theorem implies that the range consists of the integers. If the group is not torsion free, Baum and Connes conjecture ...

Hidden Markov Models are commonly trained using algorithms derived from gradient-based methods such as the Baum-Welch procedure. We describe a new representation of discrete observation HMMs that permits them to be trained using Population-Based Incremental Learning (PBIL), a variant of genetic learning that combines evolutionary optimization and hill-climbing Baluja and Caruana, 1995]. In this...

We propose several constructions for the original multiplication algorithm of D.V. and G.V. Chudnovsky in order to improve its scalar complexity. highlight set generic strategies who underlay optimization complexity, according parameterizable criteria. As an example, we apply this analysis construction type elliptic Chudnovsky2 algorithms small extensions. a case study, significantly Baum-Shokr...

Let be a countable discrete group. We prove that if the usual Baum–Connes conjecture is valid for , then the real form of Baum–Connes is also valid for . This is relevant to proving that Baum–Connes implies the stable Gromov–Lawson–Rosenberg conjecture about Riemannian metrics of positive scalar curvature. 0. Introduction The classical Baum–Connes conjecture (for a given discrete countable grou...