ASERG Research Seminar - Investigating fuzzy methods for multilingual speaker identification

We are proud to announce the first ASERG Research Seminar on 16/06/2021, 14hrs BST with Thales Aguiar de Lima, Post-graduate research student at UFRN/Brazil and researcher with LARC/USP.

Date: 16/06/2021, 14hrs BST.

Registration link (zoom link will be sent at the day of the event).

Title: Investigating fuzzy methods for multilingual speaker identification

Presenter: Thales Aguiar de Lima (UFRN/Brazil)

Abstract:

Speech is a crucial ability for humans to interact and communicate. Speech-based technologies are becoming more popular with speech interfaces, real-time translation, and budget healthcare diagnosis. Besides, the use of voice for system identification is an important and relevant topic. There are several ways of doing it, but most are dependent on the language the user speaks. However, if the idea is to create an all-inclusive and reliable system that uses speech as its input, we must take into account that people can and will speak different languages and accents. This research evaluates closed-set text-independent speaker identification systems on a multilingual setup, including both fuzzy and crisp models. Our experiments are performed using three widely spoken languages which are Portuguese, English, and Chinese. Then, we extracted 13-MFCCs, along with log-Energy and its respective delta and delta-delta from signals to use as our feature vector. We adopted four classifiers: Fuzzy C-Means, Fuzzy k-Nearest Neighbours, k-Nearest Neighbours, and Support Vector Machines. Initial tests indicated the systems have certain robustness on multiple languages. Where results with more languages decreases our accuracy; however our investigation suggests these impacts are from number of classes.