Nonparallel high-quality audio super resolution with domain adaptation and resampling CycleGANs
R Yoneyama, R Yamamoto… - ICASSP 2023-2023 …, 2023 - ieeexplore.ieee.org
Neural audio super-resolution models are typically trained on low-and high-resolution audio
signal pairs. Although these methods achieve highly accurate super-resolution if the …
signal pairs. Although these methods achieve highly accurate super-resolution if the …
Time-domain speech super-resolution with gan based modeling for telephony speaker verification
Automatic Speaker Verification (ASV) technology has become commonplace in virtual
assistants. However, its performance suffers when there is a mismatch between the train and …
assistants. However, its performance suffers when there is a mismatch between the train and …
Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition
Speech super-resolution/Bandwidth Extension (BWE) can improve downstream tasks like
Automatic Speaker Verification (ASV). We introduce a simple novel technique called Self …
Automatic Speaker Verification (ASV). We introduce a simple novel technique called Self …
CI-Mix: cut instance mix for robust speaker verification
Y Duan, Y Long, Y Li - International Journal of Speech Technology, 2023 - Springer
Data augmentation is commonly used to help build a robust speaker verification system,
especially when resources are limited. In this paper, we generalize the idea of CutMix to cut …
especially when resources are limited. In this paper, we generalize the idea of CutMix to cut …
Robust Speaker Recognition using Perceptual and Adversarial Speech Enhancement
S Kataria - 2023 - jscholarship.library.jhu.edu
Abstract In Automatic Speaker Verification (ASV), we determine whether the speaker in the
test utterance is identical to the previously enrolled speaker. Deep learning has significantly …
test utterance is identical to the previously enrolled speaker. Deep learning has significantly …