Results 1 - 10 of 1,897

The Aurora Experimental Framework for the Performance Evaluation of Speech Recognition Systems under Noisy Conditions

by David Pearce, Hans-günter Hirsch, Ericsson Eurolab Deutschland Gmbh - in ISCA ITRW ASR2000 , 2000
"... This paper describes a database designed to evaluate the performance of speech recognition algorithms in noisy conditions. The database may either be used to measure frontend feature extraction algorithms, using a defined HMM recognition back-end, or complete recognition systems. The source speech f ..."
Abstract - Cited by 534 (6 self) - Add to MetaCart
This paper describes a database designed to evaluate the performance of speech recognition algorithms in noisy conditions. The database may either be used to measure frontend feature extraction algorithms, using a defined HMM recognition back-end, or complete recognition systems. The source speech

Simulation, verification, automated composition of web services

by Srini Narayanan, Sheila A. Mcilraith - In WWW , 2002
"... Web services-- Web-accessible programs and devices – are a key application area for the Semantic Web. With the proliferation of Web services and the evolution towards the Semantic Web comes the opportunity to automate various Web services tasks. Our objective is to enable markup and automated reason ..."
Abstract - Cited by 391 (7 self) - Add to MetaCart
. Finally, we present an implementation of our analysis techniques. This implementation takes as input a DAML-S description of a Web service, automatically generates a Petri Net and performs the desired analysis. Such a tool has broad applicability both as a back end to existing manual Web service

An overview of data warehousing and OLAP technology

by Surajit Chaudhuri, Umeshwar Dayal - SIGMOD Record , 1997
"... Data warehousing and on-line analytical processing (OLAP) are essential elements of decision support, which has increasingly become a focus of the database industry. Many commercial products and services are now available, and all of the principal database management system vendors now have offering ..."
Abstract - Cited by 386 (3 self) - Add to MetaCart
back end tools for extracting, cleaning and loading data into a data warehouse; multidimensional data models typical of OLAP; front end client tools for querying and data analysis; server extensions for efficient query processing; and tools for metadata management and for managing the warehouse

On-Line Q-Learning Using Connectionist Systems

by G. A. Rummery, M. Niranjan , 1994
"... Reinforcement learning algorithms are a powerful machine learning technique. However, much of the work on these algorithms has been developed with regard to discrete finite-state Markovian problems, which is too restrictive for many real-world environments. Therefore, it is desirable to extend these ..."
Abstract - Cited by 381 (1 self) - Add to MetaCart
these methods to high dimensional continuous state-spaces, which requires the use of function approximation to generalise the information learnt by the system. In this report, the use of back-propagation neural networks (Rumelhart, Hinton and Williams 1986) is considered in this context. We consider a number

IRs and their specification in the PAGODE back-end generator

by Philippe Canalda, Lucile Cognard, Annie Despland, Monique Mazaud, François Thomasset, Domaine De Voluceau , 1996
"... In this paper, we present an approach to handle the automatic generation of back-ends from a completely declarative specification of the target machine that does not require any knowledge of the code generation process. This paper mainly focuses on the various levels of intermediate representations ..."
Abstract - Add to MetaCart
used in a back-end based on the Pagode system. This approach has been validated by the production of a C-SPARC compiler. 1 Introduction High level languages and machine languages have different computation models. The compilation process can be split into several translation phases. Usually, a front-end

Model-Based Testing for Verification Back-ends ⋆

by Cyrille Artho, Armin Biere, Martina Seidl
"... Abstract. Many verification tools used in practice rely on sophisticated SAT and SMT solvers. These reasoning engines are assumed and expected to be correct, but, in general, too complex to be fully verified. Therefore, effective testing techniques have to be employed. In this paper, we show how to ..."
Abstract - Cited by 4 (4 self) - Add to MetaCart
to employ model-based testing (MBT) to test sequences of application programming interface (API) calls and different system configurations. We applied this approach to our SAT solver Lingeling and compared it to existing testing approaches, revealing the effectiveness of MBT for the development of reliable

Improving Automatic Speaker Verification Using Front-end and Back-end diversity

by Jia Min Karen Kua , 2012
"... Technologies that exploit biometrics can potentially be applied to the identification and verification of individuals for controlling access to secured areas or materials. Among these technologies, automatic speaker verification systems are of growing interest, as they are the least invasive and t ..."
Abstract - Add to MetaCart
modelling. In this regard, the relative contributions of the acoustic and speaker modelling ‘stages’ on the speaker recognition performance across different features are investigated. The investigation conducted through the use of clustering comparison measures suggests that front-end diversity, and hence

AN INVESTIGATION ON BACK-END FOR SPEAKER RECOGNITION IN MULTI-SESSION ENROLLMENT

by Gang Liu, Taufiq Hasan, Hynek Bořil, John H. L. Hansen
"... This study explores various back-end classifiers for robust speaker recognition in multi-session enrollment, with emphasis on optimal utilization and organization of speaker information present in the development data. Our objective is to construct a highly discriminative back-end framework by fusin ..."
Abstract - Cited by 10 (6 self) - Add to MetaCart
by fusing several back-ends on an i-vector system framework. It is demonstrated that, by using different information/data configuration and modeling schemes, performance of the fused system can be significantly improved compared to an individual system using a single front-end and back-end. Averaged across

DARPA Communicator dialog travel planning systems: The June 2000 data collection

by M. Walker, J. Aberdeen, J. Bol, E. Bratt, J. Garofolo, L. Hirschman, A. Le, S. Lee, K. Papineni, B. Pellom, J. Polifroni, A. Potamianos, P. Prabhu, A. Rudnicky, S. Seneff, D. Stallard, S. Whittaker - In Eurospeech 2001 , 2001
"... This paper describes results of an experiment with 9 different DARPA Communicator Systems who participated in the June 2000 data collection. All systems supported travel planning and utilized some form of mixed-initiative interaction. However they varied in several critical dimensions: (1) They targ ..."
Abstract - Cited by 39 (10 self) - Add to MetaCart
) They targeted different back-end databases for travel information; (2) The used different modules for ASR, NLU, TTS and dialog management. We describe the experimental design, the approach to data collection, the metrics collected, and results comparing the systems. 1.

Exploring ANN Back-Ends for i-Vector Based Speaker Age Estimation

by Anna Fedorova, Ondrej Glembek, Tomi Kinnunen
"... We address the problem of speaker age estimation using i-vectors. We first compare different i-vector extraction setups and then focus on (shallow) artificial neural net (ANN) back-ends. We explore ANN architecture, training algorithm and ANN ensembles. The results on NIST 2008 and 2010 SRE data ind ..."
Abstract - Add to MetaCart
We address the problem of speaker age estimation using i-vectors. We first compare different i-vector extraction setups and then focus on (shallow) artificial neural net (ANN) back-ends. We explore ANN architecture, training algorithm and ANN ensembles. The results on NIST 2008 and 2010 SRE data
Results 1 - 10 of 1,897