Compensation of utterance length for speaker verification
نویسندگان
چکیده
The effect of utterance length on the estimation of the likelihood of a speaker has previously seen a brief treatment in past works. In many speaker recognition evaluations, the utterances were typically configured to have a relatively consistent length. This paper investigates the effect of varying enrollment and test utterance lengths on the score distributions and consequently their effect on performance. In addition, this study examines the mixing of a number of variable training length utterance trials in a single evaluation. To address this problem, a parametric solution using splines is proposed and is shown to significantly reduce the error in the conducted experiments.
منابع مشابه
Score-level compensation of extreme speech duration variability in speaker verification
In this work we aim at compensating the degrading effects of utterance length variability of speaker verification systems, which appear in many typical applications such as forensics. The paper concentrates in the score misalignments due to different utterance lengths, proposing several algorithms for its normalization. In order to test the proposed methods, we have built two corpora from NIST ...
متن کاملDomain adaptation based Speaker Recognition on Short Utterances
This paper explores how the inand out-domain probabilistic linear discriminant analysis (PLDA) speaker verification behave when enrolment and verification lengths are reduced. Experiment studies have found that when full-length utterance is used for evaluation, in-domain PLDA approach shows more than 28% improvement in EER and DCF values over out-domain PLDA approach and when short utterances a...
متن کاملShort Utterance Variance Modelling and Utterance Partitioning for PLDA Speaker Verification
This paper analyses the short utterance probabilistic linear discriminant analysis (PLDA) speaker verification with utterance partitioning and short utterance variance (SUV) modelling approaches. Experimental studies have found that instead of using single long-utterance as enrolment data, if long enrolledutterance is partitioned into multiple short utterances and average of short utterance i-v...
متن کاملImproving Short Utterance PLDA Speaker Verification using SUV Modelling and Utterance Partitioning Approach
This paper analyses the short utterance probabilistic linear discriminant analysis (PLDA) speaker verification with utterance partitioning and short utterance variance (SUV) modelling approaches. Experimental studies have found that instead of using single long-utterance as enrolment data, if long enrolledutterance is partitioned into multiple short utterances and average of short utterance i-v...
متن کاملFactor analysis based channel compensation in speaker verification
This report describes a powerful channel compensation method for the text-independent speaker verification task. This powerful method is developed in the LRDE Speaker Verification framework. The purpose of a text-independent speaker verification system is to check whether a hypothesised speaker is really the author of a speech utterance. The channel compensation problem arises when training dat...
متن کامل