Robust identification from band-limited data

Limited data speaker identification

In this paper, the task of identifying the speaker using limited training and testing data is addressed. Speaker identification system is viewed as four stages namely, analysis, feature extraction, modelling and testing. The speaker identification performance depends on the techniques employed in these stages. As demonstrated by different experiments, in case of limited training and testing dat...

Multivariate Cepstral Feature Compensation on Band-limited Data for Robust Speech Recognition

This paper describes a new method for compensating bandwidth mismatch for automatic speech recognition using multivariate linear combinations of feature vector components. It is shown that multivariate compensation is superior to methods based on linear compensations of individual features. Performance is evaluated on a real microphone-telephone mismatch condition (this involves noise compensat...

Robust control from data via uncertainty model sets identification

In this paper an integrated robust identification and control design procedure is proposed. The plant to be controlled is supposed to be linear, time invariant, stable, possibly infinite dimensional and a set of noisecorrupted input–output measurements is supposed to be available. The emphasis is placed on the design of controllers guaranteeing robust stability and robust performances, and on t...

Audio data hiding by use of band-limited random sequences

This paper proposes the use of band-limited random sequences to introduce further flexibility in the spread spectrum based audio data hiding. To realize the sub-band data hiding, a systematic method is developed in order to generate band-limited and orthonormal random sequences of any length. In experiments, we evaluated the selective use of frequency channels to be used for information embeddi...

Band-limited Functions: / / -convergence