Speaker distinguishing distances: a comparative study

Abstract

Speaker discrimination is a vital aspect of speaker recognition applications such as speaker identification, verification, clustering, indexing and change-point detection. These tasks are usually performed using distance-based approaches to compare speaker models or features from homogeneous speaker segments in order to determine whether or not they belong to the same speaker. Several distance measures and features have been examined for all the different applications, however, no single distance or feature has been reported to perform optimally for all applications in all conditions. In this paper, a thorough analysis is made to determine the behavior of some frequently used distance measures, as well as features, in distinguishing speakers for different data lengths. Measures studied include the Mahalanobis distance, Kullback-Leibler (KL) distance, T 2 statistic, Hellinger distance, Bhattacharyya distance, Generalized Likelihood Ratio (GLR), Levenne distance, L 2 and L ∞ distances. The Mel-Scale Frequency Cepstral Coefficient (MFCC), Linear Predictive Cepstral Coefficients (LPCC), Line Spectral Pairs (LSP) and the Log Area Ratios (LAR) comprise the features investigated. The usefulness of these measures is studied for different data lengths. Generally, a larger data size for each speaker results in better speaker A.N. Iyer ( ) differentiating capability, as more information can be taken into account. However, in some applications such as segmentation of telephone data, speakers change frequently, making it impossible to obtain large speaker-consistent utterances (especially when speaker change-points are unknown). A metric is defined for determining the probability of speaker discrimination error obtainable for each distance measure using each feature set, and the effect of data size on this probability is observed. Furthermore, simple distancebased speaker identification and clustering systems are developed, and the performances of each distance and feature for various data sizes are evaluated on these systems in order to illustrate the importance of choosing the appropriate distance and feature for each application. Results show that for tasks which do not involve any limitation of data length, such as speaker identification, the Kullback Leibler distance with the MFCCs yield the highest speaker differentiation performance, which is comparable to results obtained using more complex state-of-the-art speaker identification systems. Results also indicate that the Hellinger and Bhattacharyya distances with the LSPs yield the best performance for small data sizes.

An Unsupervised Approach to Cochannel Speech Separation

“…In speaker clustering, various parametric distance functions were proposed to measure speaker differences [17]. These distance functions are often derived by assuming a certain parametric distribution on the data.…”

Feature Extraction for Change-Point Detection Using Stationary Subspace Analysis

“…For a large family of general segmentation algorithms, state changes are detected based on comparing the empirical distributions between windows of the time series [14,15,18]. Estimating and comparing probability densities is a difficult statistical problem, particularly in high dimensions.…”

Βελτίωση Της Ποιότητας Συνθετικής Φωνής Και Εφαρμογή Σε Σύγχρονα Τηλεπικοινωνιακά Περιβάλλοντα Και Υπηρεσίες

“…Στο πλαίσιο της διατριβής εξετάζεται η ανάλυση ανά φώνημα και η αναπαράσταση κάθε ζεύγους από συνεχόμενα πλαίσια φωνής με ένα διάνυσμα φασματικών αποστάσεων και διαφορετικών αναπαραστάσεων του σήματος φωνής. O αποτελεσματικός συνδυασμός διαφορετικών αναπαραστάσεων και διαφορετικών φασματικών αποστάσεων αναμένεται να επαυξήσει την συνολική απόδοση και να διακρίνει καλύτερα τις δύο τάξεις στο συγκεκριμένο πρόβλημα [Garau, 2008;Iyer, 2009;Vepa, 2004]. Τα διανύσματα αυτά χρησιμοποιούνται για την εκπαίδευση του ταξινομητή μιας τάξης.…”