Feature selection via dynamic programming for text-independent speaker identification

Cheung, Ronald; Eisenstein, Bruce A.

doi:10.1109/tassp.1978.1163142

Cited by 28 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This contrasts with previously reported work [4][12] where, a theoretical criterion function was used as a measure of effectiveness. In this system, error rate depends on the decision threshold, hence we consider an empirical error rate (false acceptance rate) rather than its theoretical counterpart.…”

Section: The Proposed Optimisation Methodscontrasting

confidence: 76%

See 1 more Smart Citation

Selection of speaker independent feature for a speaker verification system

Pandit

Kittler²,

Matas³

Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170)

View full text Add to dashboard Cite

show abstract

Section: The Proposed Optimisation Methodscontrasting

confidence: 76%

“…This paper addresses the problem of selecting discriminative features from the input set of acoustic signal descriptors. This problem in the context of speech recognition and speaker recognition has already been addressed in earlier studies [4] [3] [13].…”

Section: Introductionmentioning

confidence: 99%

Selection of speaker independent feature for a speaker verification system

Pandit

Kittler²,

Matas³

Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170)

View full text Add to dashboard Cite

show abstract

“…Therefore, before predicting software effort, we should firstly decide which features are useful for the specific prediction task. This is referred to as feature subset selection (FSS) [9,27,43,19], which is the process of identifying and removing as much irrelevant and redundant information as possible from an original feature set for the purpose of providing better prediction accuracy.…”

Section: Selecting Feature Subset With Gramentioning

confidence: 99%

Predicting software project effort: A grey relational analysis based method

Song

Shepperd

2011

Expert Systems with Applications

View full text Add to dashboard Cite

The inherent uncertainty of the software development process presents particular challenges for software effort prediction. We need to systematically address missing data values, outlier detection, feature subset selection and the continuous evolution of predictions as the project unfolds, and all of this in the context of data-starvation and noisy data. However, in this paper, we particularly focus on outlier detection, feature subset selection, and effort prediction at an early stage of a project. We propose a novel approach of using Grey Relational Analysis (GRA) from Grey System Theory (GST), which is a recently developed system engineering theory based on the uncertainty of small samples. In this work we address some of the theoretical challenges in applying GRA to outlier detection, feature subset selection, and effort prediction, and then evaluate our approach on five publicly available industrial data sets using both stepwise regression and Analogy as benchmarks. The results are very encouraging in the sense of being comparable or better than other machine learning techniques and thus indicate that the method has considerable potential.

show abstract

“…The hybrid approach of soft computing techniques utilizes some bit of concepts from forward-backward dynamic programming and some bit of neural-networks. The work done by Fernando Bacao et al (2005), S. H. Ling et al (2007), H. Sakoe et al (1997, R. S. Chang et al (1978), and C. Y. Chang et al (1973), have been extended by considering eight constraints for searching the AWM using concepts of genetic algorithm (GA), for the best match of the uttered phrase.…”

Section: Algorithm -3: Procedures To Compute Weight (S)mentioning

confidence: 99%