Reformulating Speaker Diarization as Community Detection With Emphasis On Topological Structure
Clustering-based speaker diarization has stood firm as one of the major approaches in reality, despite recent development in end-to-end diarization. However, clustering methods have not been explored extensively for speaker diarization. Commonly-used methods such as k-means, spectral clustering, and...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Clustering-based speaker diarization has stood firm as one of the major
approaches in reality, despite recent development in end-to-end diarization.
However, clustering methods have not been explored extensively for speaker
diarization. Commonly-used methods such as k-means, spectral clustering, and
agglomerative hierarchical clustering only take into account properties such as
proximity and relative densities. In this paper we propose to view
clustering-based diarization as a community detection problem. By doing so the
topological structure is considered. This work has four major contributions.
First it is shown that Leiden community detection algorithm significantly
outperforms the previous methods on the clustering of speaker-segments. Second,
we propose to use uniform manifold approximation to reduce dimension while
retaining global and local topological structure. Third, a masked filtering
approach is introduced to extract "clean" speaker embeddings. Finally, the
community structure is applied to an end-to-end post-processing network to
obtain diarization results. The final system presents a relative DER reduction
of up to 70 percent. The breakdown contribution of each component is analyzed. |
---|---|
DOI: | 10.48550/arxiv.2204.12112 |