Search

27 Jul 2020: Abstract for niesler_tr265. Cambridge University Engineering Department Technical Report CUED/F-INFENG/TR265. COMPARATIVE EVALUATION OF WORD- AND CATEGORY-BASED LANGUAGE MODELS. Thomas Niesler and Phil Woodland. July 1996. Conventional n-gram

27 Jul 2020: In this paper we extend the HME to classification and results are reported for three common classification benchmark tests: Exclusive-Or, N-input Parity and Two Spirals.

27 Jul 2020: Because the compensation is word-dependent, its application needs to be hypothesis-driven on the test material.

7 Oct 2001: The final HTK system yielded an overall word error rate of 22.0% on the 1996 unpartitioned broadcast news development test data and just 16.2% on the evaluation test set - ... Work on relevance feedback, both on the the test collection, and on a (larger)

27 Jul 2020: The results show that the proposed method is very much faster yet performs acceptably compared to conventional systems which depend on keyword-specific training or prior knowledge of the test set

27 Jul 2020: An implementation is outlined and demonstrated on test sequences containing two motions.

27 Jul 2020: The paper also presents results on a new set of 60 queries with assessments for the TREC-6 test document data used for development purposes, and analyses the relationship between recognition

27 Jul 2020: It is found that, in most cases, the commonly-used cross-correlation does not perform as well as some other measures, such as the chi squared test or the sum of

27 Jul 2020: Both these schemes require no a-priori thresholding information. An initial evaluation of the techniques was performed using data from the ARPA 1994 test data.

27 Jul 2020: Here we address the problem of contaminations (e.g. occlusion, shadows) in test images which have not explicitly been encountered in training data.