Automatic speaker identification using unsupervised learning

• Grant number: 15/07934-4
• Support Opportunities: Scholarships in Brazil - Master
• Start date: June 01, 2015
• End date: May 31, 2017
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Daniel Carlos Guimarães Pedronette
• Grantee: Victor de Abreu Campos
• Host Institution: Instituto de Geociências e Ciências Exatas (IGCE). Universidade Estadual Paulista (UNESP). Campus de Rio Claro. Rio Claro , SP, Brazil
• Associated research grant: 13/08645-0 - Re-Ranking and rank aggregation approaches for image retrieval tasks, AP.JP

Abstract

There is in human speech a wide range of information that can be analyzed by allowing the recognition and automatic identification of the speaker. The scenarios that allow applications for such systems are numerous: in forensic applications, it is possible to search a suspect through his voice in a criminal database. In recordings with various speakers, such as interviews or meetings, you can identify the participation of everyone involved. In intelligent systems, you can identify the user and adapt according to your preferences interfaces. However, as with many multimedia content, audio is commonly represented as high dimensional vectors and distance measures are used to compare different objects. This research project aims at using unsupervised learning methods to increase the effectiveness of audio objects comparison metrics, in order to improve the accuracy of automatic speaker identification tasks. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

CAMPOS, VICTOR DE ABREU; GUIMARAES PEDRONETTE, DANIEL CARLOS. A framework for speaker retrieval and identification through unsupervised learning. COMPUTER SPEECH AND LANGUAGE, v. 58, p. 153-174, NOV 2019. (17/25908-6, 15/07934-4, 18/15597-6)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

CAMPOS, Victor de Abreu. Arcabouço para reconhecimento de locutor baseado em aprendizado não supervisionado. 2017. Master's Dissertation - Universidade Estadual Paulista (Unesp). Instituto de Biociências Letras e Ciências Exatas. São José do Rio Preto São José do Rio Preto.