Within class optimization of cepstra for speaker recognition
نویسندگان
چکیده
By identifying highly speaker speciic aspects of cep-stral features, the task of speaker recognition can be potentially simpliied. The identiication process can be performed both phonetically and in the cepstral domain. The phonetic analysis aims to determine the temporal aspects of utterances which exhibit the highest degree of speaker speciicity, while the cepstral analysis examines individual cepstra within these temporal divisions. This paper aims to complement work that has already been conducted on a phonetic basis, by performing analysis upon the individual cepstral coeecients within utterances.
منابع مشابه
Cepstral Statistics within Phonetic Subgroups
The identiication of aspects of cepstral features that contain a high degree of speaker speciicity potentially can simplify the task of speaker recognition. The identiication process can be performed both temporally and cepstrally. The temporal analysis determines which phonemes or utterances exhibit the highest degree of speaker speciicity, while the cepstral analysis examines individual cepst...
متن کاملRobust features for speech recognition systems
In this paper we propose a set of features based on group delay spectrum for speech recognition systems. These features appear to be more robust to channel variations and environmental changes compared to features based on Melspectral coefficients. The main idea is to derive cepstrumlike features from group delay spectrum instead of deriving them from power spectrum. The group delay spectrum is...
متن کاملDistance-based Gaussian mixture model for speaker recognition over the telephone
The paper considers text independent speaker identification over the telephone using short training and testing data. Gaussian Mixture Modeling (GMM) is used in the testing phase, but the parameters of the model are taken from clusters obtained for the training data by an adequate choice of feature vectors and a distance measure without optimization in the maximum likelihood (ML) sense. This di...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کامل