A reliable deepfake detector or spoofing countermeasure (CM) should be r...
We explore the use of neural synthesis for acoustic guitar from string-w...
The success of deep learning in speaker recognition relies heavily on th...
A speech spoofing countermeasure (CM) that discriminates between unseen
...
With the growing amount of musical data available, automatic instrument
...
This study aims to develop a single integrated spoofing-aware speaker
ve...
Speaker anonymization aims to conceal a speaker's identity while preserv...
Spoof localization, also called segment-level detection, is a crucial ta...
Deepfakes pose an evolving threat to cybersecurity, which calls for the
...
The use of modern vocoders in an analysis/synthesis pipeline allows us t...
With the similarity between music and speech synthesis from symbolic inp...
Methods addressing spurious correlations such as Just Train Twice (JTT,
...
A good training set for speech spoofing countermeasures requires diverse...
Finger vein recognition (FVR) systems have been commercially used, espec...
Benchmarking initiatives support the meaningful comparison of competing
...
Conventional automatic speaker verification systems can usually be decom...
The VoicePrivacy Challenge aims to promote the development of privacy
pr...
Automatic speaker verification is susceptible to various manipulations a...
In our previous work, we proposed a language-independent speaker
anonymi...
For new participants - Executive summary: (1) The task is to develop a v...
Speech enhancement (SE) methods mainly focus on recovering clean speech ...
We present the first edition of the VoiceMOS Challenge, a scientific eve...
Speaker anonymization aims to protect the privacy of speakers while
pres...
The performance of spoofing countermeasure systems depends fundamentally...
Recent advances in deep learning have led to substantial improvements in...
As automatic speaker verification (ASV) systems are vulnerable to spoofi...
Voice-based human-machine interfaces with an automatic speaker verificat...
Estimating the mask-wearing ratio in public places is important as it en...
Self-supervised speech model is a rapid progressing research topic, and ...
An effective approach to automatically predict the subjective rating for...
Emotional and controllable speech synthesis is a topic that has received...
Conventional speech spoofing countermeasures (CMs) are designed to make ...
Are end-to-end text-to-speech (TTS) models over-parametrized? To what ex...
A large and growing amount of speech content in real-life scenarios is b...
Face authentication is now widely used, especially on mobile devices, ra...
This paper presents the results and analyses stemming from the first
Voi...
ASVspoof 2021 is the forth edition in the series of bi-annual challenges...
The automatic speaker verification spoofing and countermeasures (ASVspoo...
For many decades, research in speech technologies has focused upon impro...
The proliferation of deepfake media is raising concerns among the public...
In this paper, we provide a series of multi-tasking benchmarks for
simul...
Timbre representations of musical instruments, essential for diverse
app...
Neural evaluation metrics derived for numerous speech generation tasks h...
Generally speaking, the main objective when training a neural speech
syn...
Whether it be for results summarization, or the analysis of classifier
f...
Evidence-based fact checking aims to verify the truthfulness of a claim
...
Shared challenges provide a venue for comparing systems trained on commo...
This work examines the content and usefulness of disentangled phone and
...
Speech synthesis and music audio generation from symbolic input differ i...
The intelligibility of speech severely degrades in the presence of
envir...