Emotional Styles Hide in Deep Speaker Embeddings: Disentangle Deep Speaker Embeddings for Speaker Clustering

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lin, Chaohao, Zheng, Xu, Wu, Kaida, Xiang, Peihao, Bai, Ou
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909812876378112
author Lin, Chaohao
Zheng, Xu
Wu, Kaida
Xiang, Peihao
Bai, Ou
author_facet Lin, Chaohao
Zheng, Xu
Wu, Kaida
Xiang, Peihao
Bai, Ou
contents Speaker clustering is the task of identifying the unique speakers in a set of audio recordings (each belonging to exactly one speaker) without knowing who and how many speakers are present in the entire data, which is essential for speaker diarization processes. Recently, off-the-shelf deep speaker embedding models have been leveraged to capture speaker characteristics. However, speeches containing emotional expressions pose significant challenges, often affecting the accuracy of speaker embeddings and leading to a decline in speaker clustering performance. To tackle this problem, we propose DTG-VAE, a novel disentanglement method that enhances clustering within a Variational Autoencoder (VAE) framework. This study reveals a direct link between emotional states and the effectiveness of deep speaker embeddings. As demonstrated in our experiments, DTG-VAE extracts more robust speaker embeddings and significantly enhances speaker clustering performance.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23358
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Emotional Styles Hide in Deep Speaker Embeddings: Disentangle Deep Speaker Embeddings for Speaker Clustering
Lin, Chaohao
Zheng, Xu
Wu, Kaida
Xiang, Peihao
Bai, Ou
Sound
Audio and Speech Processing
Speaker clustering is the task of identifying the unique speakers in a set of audio recordings (each belonging to exactly one speaker) without knowing who and how many speakers are present in the entire data, which is essential for speaker diarization processes. Recently, off-the-shelf deep speaker embedding models have been leveraged to capture speaker characteristics. However, speeches containing emotional expressions pose significant challenges, often affecting the accuracy of speaker embeddings and leading to a decline in speaker clustering performance. To tackle this problem, we propose DTG-VAE, a novel disentanglement method that enhances clustering within a Variational Autoencoder (VAE) framework. This study reveals a direct link between emotional states and the effectiveness of deep speaker embeddings. As demonstrated in our experiments, DTG-VAE extracts more robust speaker embeddings and significantly enhances speaker clustering performance.
title Emotional Styles Hide in Deep Speaker Embeddings: Disentangle Deep Speaker Embeddings for Speaker Clustering
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2509.23358