Target Speech Separation with Dual-Path RNN

Student: Ievleva Aleksandra

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2024

Separating a specific speaker’s voice from an audio recording containing overlapping speech from multiple speakers presents a complex challenge in audio processing, known as target speech separation. Despite recent advancements in methods for separating target speech, computational and memory costs remain significant barriers for many existing solutions, limiting their practical application. This study explores an approach to the TSS problem that utilizes a lightweight Dual-Path Recurrent Neural Network (DPRNN) to enhance the efficiency and quality of speech separation.

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