Unsupervised model adaptation
نویسنده
چکیده
This paper deals with unsupervised model adaptation for speaker recognition. Two adaptation schemes are proposed, the first one is based on a test by test model adaptation and the second one proposes a batch mode, where the adaptation is performed using a set of tests before computing the decision score for each of them. The experiments are conducted thanks to the NIST SRE 2005 database. This paper shows clearly the interest of unsupervised model adaptation when enough test data is available (batch mode) and the intrinsic difficulty of an online (test by test) adaptation mode.
منابع مشابه
Deep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملUnsupervised acoustic model adaptation based on phoneme error minimization
In this paper, a new decoding method for unsupervised acoustic model adaptation is presented. In unsupervised adaptation framework, the effectiveness of adaptation process is greatly affected by the mis-recognized labels. Therefore, selection of the adaptation data guided by the confidence measures is effective in unsupervised adaptation. We propose phoneme error minimization framework for exac...
متن کاملUnsupervised Acoustic Model Adaptati Minimizatio
In this paper, a new decoding method for unsupervised acoustic model adaptation is presented. In unsupervised adaptation framework, the effectiveness of adaptation process is greatly affected by the mis-recognized labels. Therefore, selection of the adaptation data guided by the confidence measures is effective in unsupervised adaptation. We propose phoneme error minimization framework for exac...
متن کاملOn comparing and combining intra-speaker variability compensation and unsupervised model adaptation in speaker verification
In this paper an unsupervised intra-speaker variability compensation method, ISVC, and unsupervised model adaptation are tested to address the problem of limited enrolling data in text-dependent speaker verification. In contrast to model adaptation methods, ISVC is memoryless with respect to previous verification attempts. As shown here, unsupervised model adaptation can lead to substantial imp...
متن کاملA Continuous Unsupervised Adaptation Method for Speaker Verification
This paper deals with unsupervised model adaptation for speaker verification. We proposed a new method for updating speaker models using all test information incoming in the system. This is a continuous adaptation method which relies on the probability of the test trial belonging to the target speaker. Our adaptation scheme is evaluated in the framework of the NIST SR...
متن کامل