Search Results for author:
Found 8 papers, 2 papers with code
Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting
Our results demonstrate that catastrophic forgetting can be overcome by our methods without degrading the fine-tuning performance, and using the Kronecker factored approximations produces a better preservation of the pre-training knowledge than the diagonal ones.
Vulnerability of Automatic Identity Recognition to Audio-Visual Deepfakes
From the publicly available speech dataset LibriTTS, we also created a separate database of only audio deepfakes LibriTTS-DF using several latest text to speech methods: YourTTS, Adaspeech, and TorToiSe.
An investigation into the adaptability of a diffusion-based TTS model
Given the recent success of diffusion in producing natural-sounding synthetic speech, we investigate how diffusion can be used in speaker adaptive TTS.
HyperMixer: An MLP-based Low Cost Alternative to Transformers
We find that existing architectures such as MLPMixer, which achieves token mixing through a static MLP applied to each feature independently, are too detached from the inductive biases required for natural language understanding.
Stable and Compact Face Recognition via Unlabeled Data Driven Sparse Representation-Based Classification
The proposed model aims to mine the hidden semantic information and intrinsic structure information of all available data, which is suitable for few labeled samples and proportion imbalance between labeled samples and unlabeled samples problems in frontal face recognition.
Can We Trust Deep Speech Prior?
Recently, speech enhancement (SE) based on deep speech prior has attracted much attention, such as the variational auto-encoder with non-negative matrix factorization (VAE-NMF) architecture.
Overcomplete order-3 tensor decomposition, blind deconvolution and Gaussian mixture models
We propose a new algorithm for tensor decomposition, based on Jennrich's algorithm, and apply our new algorithmic ideas to blind deconvolution and Gaussian mixture models.
CN-CELEB: a challenging Chinese speaker recognition dataset
These datasets tend to deliver over optimistic performance and do not meet the request of research on speaker recognition in unconstrained conditions.
