On the relevance of bandwidth extension for speaker identification

TL;DR

This paper investigates whether bandwidth extension improves speaker identification accuracy by analyzing extended telephone bandwidth speech signals, demonstrating that MELCEPST features benefit from bandwidth extension in certain scenarios.

Contribution

It introduces a study on the impact of bandwidth extension on speaker recognition, including the creation of new databases and evaluation of feature parameterizations.

Findings

MELCEPST features benefit from bandwidth extension.

Bandwidth extension can improve speaker identification in specific conditions.

Created databases for bandwidth extended speech analysis.

Abstract

In this paper we discuss the relevance of bandwidth extension for speaker identification tasks. Mainly we want to study if it is possible to recognize voices that have been bandwith extended. For this purpose, we created two different databases (microphonic and ISDN) of speech signals that were bandwidth extended from telephone bandwidth ([300, 3400] Hz) to full bandwidth ([100, 8000] Hz). We have evaluated different parameterizations, and we have found that the MELCEPST parameterization can take advantage of the bandwidth extension algorithms in several situations.