13 citations · 14 across the 8 of their papers we have counts for
8 papers
DeltaFlow: Noise-Adaptive Bidirectional Gated Delta Networks for Embedded Language Flows
Guangfu Guo, Xiaoqian Lu, Linsey Pang +4
Embedded Language Flows (ELF) rely primarily on full non-causal attention for iterative denoising, repeatedly incurring quadratic sequence-mixing cost at each sampling step. Gated…
Improving Audio Question Answering with Variational Inference
Haolin Chen
Variational inference (VI) provides a principled framework for estimating posterior distributions over model parameters, enabling explicit modeling of weight uncertainty during opt…
A Bayesian Interpretation of Adaptive Low-Rank Adaptation
Haolin Chen, Philip N. Garner
Motivated by the sensitivity-based importance score of the adaptive low-rank adaptation (AdaLoRA), we utilize more theoretically supported metrics, including the signal-to-noise ra…
Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting
Haolin Chen, Philip N. Garner
We are motivated primarily by the adaptation of text-to-speech synthesis models; however we argue that more generic parameter-efficient fine-tuning (PEFT) is an appropriate framewo…
Vulnerability of Automatic Identity Recognition to Audio-Visual Deepfakes
Pavel Korshunov, Haolin Chen, Philip N. Garner +1
The task of deepfakes detection is far from being solved by speech or vision researchers. Several publicly available databases of fake synthetic video and speech were built to aid…
An investigation into the adaptability of a diffusion-based TTS model
Haolin Chen, Philip N. Garner
Given the recent success of diffusion in producing natural-sounding synthetic speech, we investigate how diffusion can be used in speaker adaptive TTS. Taking cues from more tradit…
Can We Trust Deep Speech Prior?
Ying Shi, Haolin Chen, Zhiyuan Tang +3
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) arc…
CN-CELEB: a challenging Chinese speaker recognition dataset
Yue Fan, Jiawen Kang, Lantian Li +7
Recently, researchers set an ambitious goal of conducting speaker recognition in unconstrained conditions where the variations on ambient, channel and emotion could be arbitrary. H…