The goal of this paper is to review and classify the different approaches to search in peer-to-peer networks. We then describe the approach implemented in JXTA search. JXTA is an open peer-to-peer network environment. JXTA search is a network of hubs that index the content of a peer-topeer network. Finally, we propose an organization of the JXTA search hubs, which reduces the storage and communication requirements between the hubs.

This paper describes the development of the CU-CON system which participated in the 1996 ARPA Hub 4 Evaluations. The system is based on ABBOT, a hybrid connectionist-HMM large vocabulary continuous speech recognition system developed at the Cambridge University Engineering Department by Hochberg et al. (1995). The Hub 4 Evaluation task involves the transcription of broadcast television and radio news programmes. This is an extremely demanding task for a state-of-the-art speech recognition system. Typical programmes include a wide variety of speaking styles and acoustic conditions. These range from read speech recorded in the studio to extemporaneous speech recorded over telephone channels.

In this paper we investigate a number of ensemble methods for improving the performance of connectionist acoustic models for large vocabulary continuous speech recognition. We discuss boosting, a data selection technique which results in an ensemble of models, and mixtures-ofexperts. These techniques have been applied to multilayer perceptron acoustic models used to build a hybrid connectionist-HMM speech recognition system. We present results on a number of ARPA benchmark tasks, and show that the ensemble methods lead to considerable improvements in recognition accuracy. 1. INTRODUCTION When developing a classification or prediction system it is common practice to train a number of different models, and to retain the model which exhibits the best performance on a cross-validation data set. However, reports in the statistics and neural network literature suggest that improved performance can be achieved by combining the estimates of all the available models [1, 2, 3, 4]. Systems that...

abbot is the hybrid connectionist hidden Markov model (HMM) large vocabulary continuous speech recognition system developed at Cambridge University Engineering Department.abbot makes eective use of the linear input network (LIN) adaptation technique to achieve speaker and channel adaptation.Although the LIN is eective at adapting to new speakers or a new environment (e.g. a dierent microphone), the transform is global over the input space.In this paper we describe a technique by which the transform may be made locally linear over dierent regions of the input space.The local linear transforms are combined by an additional network using a non-linear transform.This scheme falls naturally into the mixtures of experts framework.

In this paper we consider speech coding as a problem of speech modelling. In particular, prediction of parameterised speech over short time segments is performed using the Hierarchical Mixture of Experts (HME) (Jordan & Jacobs 1994). The HME gives two ad(cid:173) vantages over traditional non-linear function approximators such as the Multi-Layer Percept ron (MLP); a statistical understand(cid:173) ing of the operation of the predictor and provision of information about the performance of the predictor in the form of likelihood information and local error bars. These two issues are examined on both toy and real world problems of regression and time series prediction. In the speech coding context, we extend the principle of combining local predictions via the HME to a Vector Quantiza(cid:173) tion scheme in which fixed local codebooks are combined on-line for each observation.