Idioma:

Building a Speaker Diarization System: Lessons from VoxSRC 2023

Karamyan, Davit S. ; Kirakosyan, Grigor A.

Mathematical problems of computer science (Online), 2023-11, Vol.60, p.52-62

Texto completo disponível

Citações Citado por

Título:
Building a Speaker Diarization System: Lessons from VoxSRC 2023
Autor: Karamyan, Davit S. ; Kirakosyan, Grigor A.
É parte de: Mathematical problems of computer science (Online), 2023-11, Vol.60, p.52-62
Descrição: Speaker diarization is the process of partitioning an audio recording into segments corresponding to individual speakers. In this paper, we present a robust speaker diarization system and describe its architecture. We focus on discussing the key components necessary for building a strong diarization system, such as voice activity detection (VAD), speaker embedding, and clustering. Our system emerged as the winner in the Voxceleb Speaker Recognition Challenge (VoxSRC) 2023, a widely recognized competition for evaluating speaker diarization systems.
Idioma: Inglês

Voltar para lista de resultados