Exploring Acoustic Factor Analysis for limited test data speaker verification

Speaker verification with short utterances: a review of challenges, trends and opportunities

“…norm. Short Utterance Normalisation (SUN)-LDA, LDA, WCCN, CSS, Source Normalised Linear Discriminant Analysis (SN-LDA) [45] Baum Welch (BW) statistics estimation minimax [88] [91] evaluation of feature dimensionality feature dimension reduction, DKLT [40] performance comparison GMM-UBM, i-vector GPLDA [56] parallel system based on source feature M-PDSS, DCTILPR, score fusion [92] i-vector subspace projection modified-prior PLDA, score calibration, QMF [93] calibration and quality of speech signal QMFs from duration + SNR, stacked, matched/mismatched calibration 2016 [94] phonetic match between train and test WCCN, EFR, interactive voice response system [95] factor analysis on i-vector domain AFA, WCCN, LDA, GPLDA, score level fusion [96] phonetic content compensation ML-AFA, SUVN, score fusion [97] phonetic analysis modelling speech unit classes [98] normalise BW statistics compensation for feature sparsity in BW statistics [99] bootstrapped i-vectors truncate from test segment and integrating speaker similarities 2017 [100] development data with short utterance WCCN-LDA, SN-LDA, SN-WLDA, GPLDA [101] inter/intra-speaker variability a transform to map i-vectors onto a duration invariant latent subspace [102] i-vector length normalisation DNN-based length normalisation of i-vectors using PCs mentioned techniques, the information of utterance variation needs to be supplemented additionally to full-length i-vectors for modelling of PLDA. The work in [90] analysed the PLDA modelling with limited development data.…”

“…The work proposed a simplistic utterance-partitioning technique successfully with the conjecture that the improvement was due to apparent enhancement in the number of sessions by partitioning technique which accompanied better estimation of GPLDA parameters. The study in [95] illustrated that combination of two methods, acoustic FA (AFA) [103] and i-vector [12] can lead to a much upgraded ASV system to mitigate the issue of short utterances. MFCC features are projected onto a lower-dimensional subspace using FA based on the AFA technique.…”

“…The reports indicate that the performance for ASV can be improved considerably with better projection of speaker‐model vectors and score calculation. Although few attempts on specialised speaker‐model vector projection for short‐duration segments have been done [22, 90, 95, 98, 100] but comparatively less effort has been made in improving score computation [93]. Different distance or similarity metrics can be explored to measure the score of i ‐vector representation of speech utterances [115].…”

“…The study in [95] illustrated that combination of two methods, acoustic FA (AFA) [103] and i ‐vector [12] can lead to a much upgraded ASV system to mitigate the issue of short utterances. MFCC features are projected onto a lower‐dimensional subspace using FA based on the AFA technique.…”