[PDF][PDF] Effectiveness of Speech Demodulation-Based Features for Replay Detection.
Replay attack presents a great threat to Automatic Speaker Verification (ASV) system. The
speech can be modeled as amplitude and frequency modulated (AM-FM) signals. In this …
speech can be modeled as amplitude and frequency modulated (AM-FM) signals. In this …
Efficient text-independent speaker verification with structural Gaussian mixture models and neural network
B Xiang, T Berger - IEEE Transactions on Speech and Audio …, 2003 - ieeexplore.ieee.org
We present an integrated system with structural Gaussian mixture models (SGMMs) and a
neural network for purposes of achieving both computational efficiency and high accuracy in …
neural network for purposes of achieving both computational efficiency and high accuracy in …
Exact methods for the asymmetric traveling salesman problem
In the present chapter we concentrate on the exact solution methods for the Asymmetric TSP
proposed in the literature after the writing of the survey of [81]. In Section 2 two specific …
proposed in the literature after the writing of the survey of [81]. In Section 2 two specific …
Voice privacy using CycleGAN and time-scale modification
Abstract Extensive use of Intelligent Personal Assistants (IPA) and biometrics in our day-to-
day life asks for privacy preservation while dealing with personal data. To that effect, efforts …
day life asks for privacy preservation while dealing with personal data. To that effect, efforts …
[PDF][PDF] Spoken language conversion with accent morphing
M Huckvale, K Yanagisawa - 2007 - discovery.ucl.ac.uk
Spoken language conversion is the challenge of using synthesis systems to generate
utterances in the voice of a speaker but in a language unknown to the speaker. Previous …
utterances in the voice of a speaker but in a language unknown to the speaker. Previous …
Vector quantization based Gaussian modeling for speaker verification
J Pelecanos, S Myers, S Sridharan… - … Conference on Pattern …, 2000 - ieeexplore.ieee.org
Gaussian mixture models (GMMs) have become an established means of modeling feature
distributions in speaker recognition systems. It is useful for experimentation and practical …
distributions in speaker recognition systems. It is useful for experimentation and practical …
[图书][B] An MRI-based articulatory and acoustic study of American English liquid sounds/r/and/l
X Zhou - 2009 - search.proquest.com
Abstract In American English, the liquid sounds/r/and/l/are the most articulatorily variable
and complex sounds. They can be produced by several distinct types of tongue …
and complex sounds. They can be produced by several distinct types of tongue …
A new approach to designing a feature extractor in speaker identification based on discriminative feature extraction
C Miyajima, H Watanabe, K Tokuda, T Kitamura… - Speech …, 2001 - Elsevier
This paper presents a new framework for designing a feature extractor in a speaker
identification system based on the discriminative feature extraction (DFE) method. In order to …
identification system based on the discriminative feature extraction (DFE) method. In order to …
A novel approach to remove outliers for parallel voice conversion
Alignment is a key step before learning a mapping function between a source and a target
speaker's spectral features in various state-of-the-art parallel data Voice Conversion (VC) …
speaker's spectral features in various state-of-the-art parallel data Voice Conversion (VC) …
[PDF][PDF] Speaker Recognition and Broad Phonetic Groups.
M Antal, G Toderean - SPPRA, 2006 - academia.edu
The aim of this study is to provide a quantitative assessment of the speaker discriminating
properties of broad phonetic groups. GMM based approach to speaker modelling is used in …
properties of broad phonetic groups. GMM based approach to speaker modelling is used in …