Synthesizing dysarthric speech using multi-speaker tts for dysarthric speech recognition
M Soleymanpour, MT Johnson… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
Dysarthria is a motor speech disorder often characterized by reduced speech intelligibility
through slow, uncoordinated control of speech production muscles. Automatic Speech …
through slow, uncoordinated control of speech production muscles. Automatic Speech …
Unsupervised representation disentanglement using cross domain features and adversarial learning in variational autoencoder based voice conversion
An effective approach for voice conversion (VC) is to disentangle linguistic content from
other components in the speech signal. The effectiveness of variational autoencoder (VAE) …
other components in the speech signal. The effectiveness of variational autoencoder (VAE) …
Velody: Nonlinear vibration challenge-response for resilient user authentication
Biometrics have been widely adopted for enhancing user authentication, benefiting usability
by exploiting pervasive and collectible unique characteristics from physiological or …
by exploiting pervasive and collectible unique characteristics from physiological or …
Assessing the scope of generalized countermeasures for anti-spoofing
Most of the research on anti-spoofing countermeasures are specific to a type of spoofing
attacks, where models are trained on data of a particular nature, either synthetic or replay …
attacks, where models are trained on data of a particular nature, either synthetic or replay …
[PDF][PDF] Attention-Based Convolutional Neural Network for ASV Spoofing Detection.
In recent years, automatic speaker verification (ASV) algorithms have undergone significant
progress. They have been widely deployed in different applications, but the ASV systems …
progress. They have been widely deployed in different applications, but the ASV systems …
Data augmentation with signal companding for detection of logical access attacks
The recent advances in voice conversion (VC) and text-to-speech (TTS) make it possible to
produce natural sounding speech that poses threat to automatic speaker verification (ASV) …
produce natural sounding speech that poses threat to automatic speaker verification (ASV) …
Audio Deepfake Approaches
OA Shaaban, R Yildirim, AA Alguttar - IEEE Access, 2023 - ieeexplore.ieee.org
This paper presents a review of techniques involved in the creation and detection of audio
deepfakes, the first section provides information about general deep fakes. In the second …
deepfakes, the first section provides information about general deep fakes. In the second …
Voice mimicry attacks assisted by automatic speaker verification
In this work, we simulate a scenario, where a publicly available ASV system is used to
enhance mimicry attacks against another closed source ASV system. In specific, ASV …
enhance mimicry attacks against another closed source ASV system. In specific, ASV …
On the study of generative adversarial networks for cross-lingual voice conversion
Cross-lingual voice conversion (VC) aims to convert the source speaker's voice to sound like
that of the target speaker, when the source and target speakers speak different languages …
that of the target speaker, when the source and target speakers speak different languages …
Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesis
Neural sequence-to-sequence text-to-speech synthesis (TTS) can produce high-quality
speech directly from text or simple linguistic features such as phonemes. Unlike traditional …
speech directly from text or simple linguistic features such as phonemes. Unlike traditional …