P
Phillip L. De Leon
Researcher at New Mexico State University
Publications - 49
Citations - 971
Phillip L. De Leon is an academic researcher from New Mexico State University. The author has contributed to research in topics: Speaker recognition & Instantaneous phase. The author has an hindex of 11, co-authored 46 publications receiving 844 citations. Previous affiliations of Phillip L. De Leon include University of Colorado Boulder & University of Edinburgh.
Papers
More filters
Journal ArticleDOI
Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech
TL;DR: A new feature based on relative phase shift (RPS) is proposed, demonstrated reliable detection of synthetic speech, and shown how this classifier can be used to improve security of SV systems.
Proceedings ArticleDOI
Detection of synthetic speech for the problem of imposture
TL;DR: A HMM-based speech synthesizer is used, which creates synthetic speech for a targeted speaker through adaptation of a background model and both GMM-UBM and support vector machine (SVM) SV systems are used, reducing the vulnerability of a speaker verification (SV) system to synthetic speech.
Journal ArticleDOI
Anti-spoofing for text-independent speaker verification: an initial database, comparison of countermeasures, and human performance
Zhizheng Wu,Phillip L. De Leon,Cenk Demiroglu,Ali Khodabakhsh,Simon King,Zhen-Hua Ling,Daisuke Saito,Bryan Stewart,Tomoki Toda,Mirjam Wester,Junichi Yamagishi +10 more
TL;DR: This paper starts with a thorough analysis of the spoofing effects of five speech synthesis and eight voice conversion systems, and the vulnerability of three speaker verification systems under those attacks, and introduces a number of countermeasures to prevent spoofing attacks.
Proceedings ArticleDOI
Synthetic Speech Discrimination using Pitch Pattern Statistics Derived from Image Analysis
TL;DR: The classifier is trained using synthetic speech collected from the 2008 and 2011 Blizzard Challenge along with Festival pre-built voices and human speech from the NIST2002 corpus to discriminate between human and synthetic speech using features based on pitch patterns.
Book ChapterDOI
Speaker Recognition Anti-spoofing
Nicholas Evans,Tomi Kinnunen,Junichi Yamagishi,Junichi Yamagishi,Zhizheng Wu,Federico Alegre,Phillip L. De Leon +6 more
TL;DR: The literature shows that there is significant potential for automatic speaker verification systems to be spoofed, that significant further work is required to develop generalised countermeasures, there is a need for standard datasets, evaluation protocols and metrics and that greater emphasis should be placed on text-dependent scenarios.