CNN-Based Joint Mapping of Short and Long Utterance i-Vectors for Speaker Verification Using Short Utterances

Abstract

Text-independent speaker recognition using short utterances is a highly challenging task due to the large variation and content mismatch between short utterances. I-vector and probabilistic linear discriminant analysis (PLDA) based systems have become the standard in speaker verification applications, but they are less effective with short utterances. To address this issue, we propose a novel method, which trains a convolutional neural network (CNN) model to map the i-vectors extracted from short utterances to the corresponding long-utterance i-vectors. In order to simultaneously learn the representation of the original short-utterance i-vectors and fit the target long-version ivectors, we jointly train a supervised-regression model with an autoencoder using CNNs. The trained CNN model is then used to generate the mapped version of short-utterance i-vectors in the evaluation stage. We compare our proposed CNNbased joint mapping method with a GMM-based joint modeling method under matched and mismatched PLDA training conditions. Experimental results using the NIST SRE 2008 dataset show that the proposed technique achieves up to 30% relative improvement under duration mismatched PLDA-training conditions and outperforms the GMM-based method. The improved systems also perform better compared with the matched-length PLDA training condition using short utterances.

Development of security systems using DNN and i & x-vector classifiers

“…Speaker recognition was investigated in [16]. Gaussian mixtures were used as the main classification method for speaker recognition.…”

“…( ) 16) where N and F are the matrices composed of the zero-and first-order statistics, and is the covariance matrix of F. These i-vectors will have information of the language contained in the utterance they represent, since that is the task for which the T matrix has been trained. Voice recognition bottleneck features [35].…”

Artificial Bandwidth Extension with Memory Inclusion Using Semi-supervised Stacked Auto-encoders

“…The SSAE architecture can also be used to estimate the HB components directly from the regression layer. A similar CNN based architecture designed to regularise the mapping of short i-vectors to long i-vectors for a speaker diarization task is reported in [29]. The focus here is different, i.e., to regularise/supervise dimensionality reduction so that it preserves information critical to ABE.…”

Deep Discriminant Analysis for i-vector Based Robust Speaker Recognition

“…Since proposed in [1], i-vector has become the state-of-the-art speaker modeling technique, it is a simple but elegant factor analysis model, inspired by the Joint Factor Analysis (JFA) [2] framework. Though some researchers have been working on improving the i-vector model itself [3,4], more researchers pay attention to the compensation techniques in the i-vector space [5,6,7,8]. JFA can be regarded as a compensation method in the GMM super-vector space, which models the speaker and channel variabilities separately.…”

“…Authors in [7] proposed to use an auto-encoder to learn a projection which maps noisy i-vectors to de-noised ones. To address the short-duration problem of i-vector [20], a Convolutional Neural Network (CNN) based system was trained in [8] to map the i-vectors extracted from short utterances to the corresponding long-utterance i-vectors.…”