Search Results for author:
Found 7 papers, 4 papers with code
Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss
Diffusion models are known to be vulnerable to outliers in training data.
A Semi-Supervised Deep Learning Approach to Dataset Collection for Query-By-Humming Task
To expand our dataset, we employ a semi-supervised model training pipeline that leverages the QbH task as a specialized case of cover song identification (CSI) task.
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
Voice conversion is a common speech synthesis task which can be solved in different ways depending on a particular real-world scenario.
Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing for flexible inference schemes.
Ranked #3 on
Text-To-Speech Synthesis
on LJSpeech
(using extra training data)
Fine-tuning of Language Models with Discriminator
Cross-entropy loss is a common choice when it comes to multiclass classification tasks and language modeling in particular.
Distributed Fine-tuning of Language Models on Private Data
In language modeling, users’ language (e. g. in private messaging) could change in a year and be completely different from what we observe in publicly available data.
Differentially Private Distributed Learning for Language Modeling Tasks
One of the big challenges in machine learning applications is that training data can be different from the real-world data faced by the algorithm.
