Gender Recognition by Voice Using an Improved Self-Labeled Algorithm

TLDR

Speech recognition is applied in human‑to‑machine interaction, call sorting, and video tagging, and recent work combines ensemble learning with semi‑supervised frameworks to improve classifier accuracy. The study aims to perform gender recognition from voice using a novel ensemble semi‑supervised self‑labeled algorithm. The algorithm employs an ensemble of classifiers trained in a semi‑supervised self‑labeling scheme to extract voice features for gender classification. Preliminary experiments show the algorithm achieves high accuracy, yielding stable and robust predictive models.

Abstract

Speech recognition has various applications including human to machine interaction, sorting of telephone calls by gender categorization, video categorization with tagging and so on. Currently, machine learning is a popular trend which has been widely utilized in various fields and applications, exploiting the recent development in digital technologies and the advantage of storage capabilities from electronic media. Recently, research focuses on the combination of ensemble learning techniques with the semi-supervised learning framework aiming to build more accurate classifiers. In this paper, we focus on gender recognition by voice utilizing a new ensemble semi-supervised self-labeled algorithm. Our preliminary numerical experiments demonstrate the classification efficiency of the proposed algorithm in terms of accuracy, leading to the development of stable and robust predictive models.