Confidence Measure Based Model Adaptation for Speaker Verification
نویسنده
چکیده
Confidence measures are expected give a measure of reliability on the result of a speech/speaker recognition system. Most commonly used confidence measures are based on posterior word or phoneme probabilities which can be obtained from the output of the recognizer. In this paper we introduced a linear interpretation of posterior probability based confidence measure by using inverse Fisher transformation. Speaker adaptation consists in updating model parameters of a speaker independent model to have a better representation of the current speaker. Confidence measures give a more reliable selection criteria to select the utterances which best represents the speaker. A linear interpretation of confidence measure is very important to select the most representative data for adaptation.
منابع مشابه
Speaker Model Adaptation Based on Confidence Score
Original scientific paper Confidence measures are expected to give a measure of reliability on the result of a speech/speaker recognition system. Most commonly used confidence measures are based on posterior word or phoneme probabilities which can be obtained from the output of the recognizer. In this paper we introduced a linear interpretation of posterior probability based confidence measure ...
متن کاملSpeaker adaptation based on confidence-weighted training
This paper presents a novel method to enhance the performance of traditional speaker adaptation algorithm using discriminative adaptation procedure based on a novel confidence measure and non-linear weighting. Regardless of the distribution of the adaptation data, traditional model adaptation methods incorporate the adaptation data undiscriminatingly. When the data size is small and the paramet...
متن کاملOn-Line Unsupervised Adaptation in Speaker Verification: Confidence-Based Updates and Improved Parameter Estimation
This paper presents the second part of a new approach to on-line unsupervised adaptation in speaker verification. The new approach extends previous work in the literature by (1) improving performance on the enrollment handset-type when adapting on a different handset-type (e.g., improving performance on cellular when adapting on a landline office phone), (2) accomplishing this cross channel imp...
متن کاملConfidence measure based unsupervised target model adaptation for speaker verification
This paper proposes a new method for updating online the client models of a speaker recognition system using the test data. This problem is called unsupervised adaptation. The main idea of the proposed approach is to adapt the client model using the complete set of data gathered from the successive test, without deciding if the test data belongs to the client or to an impostor. The adaptation p...
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