Progressive Distillation for Faster Sampling in Diffusion Models for Speech Generation

Student: Voronin Konstantin

Educational Programme: Software Engineering (Bachelor)

Year of Graduation: 2024

Recent advancements in deep learning have led to significant progress in speech synthesis. Diffusion models have emerged as a promising approach for generating complex data. These models use iterative noise application to model probability distributions, resulting in high-quality speech synthesis. Although they have shown impressive results, challenges remain in real-time generation and scalability. This paper examines the potential of Progressive Distillation in addressing these challenges. Our approach aims to enable real-time speech generation of speech by accelerating the sampling process while maintaining sample quality. Keywords: speech synthesis, deep generative models, diffusion models, progressive distillation, real-time generation

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses