paper-with-me

홈 › Papers

Adapting Speaker Embeddings for Speaker Diarisation

2021-04-07 · Youngki Kwon, Jee-weon Jung, Hee-Soo Heo, You Jin Kim, Bong-Jin Lee, Joon Son Chung

The goal of this paper is to adapt speaker embeddings for solving the problem of speaker diarisation. The quality of speaker embeddings is paramount to the performance of speaker diarisation systems. Despite this, prior works in the field have directly used embeddings designed only to be effective on the speaker verification task. In this paper, we propose three techniques that can be used to better adapt the speaker embeddings for diarisation: dimensionality reduction, attention-based embedding aggregation, and non-speech clustering. A wide range of experiments is performed on various challenging datasets. The results demonstrate that all three techniques contribute positively to the performance of the diarisation system achieving an average relative improvement of 25.07% in terms of diarisation error rate over the baseline.

📄 PDF Abstract BibTeX arXiv:2104.02879

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringDimensionality ReductionSpeaker Verification

Similar Papers 제목 키워드 기반

Content-Aware Speaker Embeddings for Speaker Diarisation

2021-02-12 · G. Sun, D. Liu, C. Zhang, P. C. Woodland

Recent speaker diarisation systems often convert variable length speech segments into fixed-length vector representations for speaker clustering, which are known as speaker embeddings. In this paper, the content-aware sp…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)ClusteringSpeaker Recognition+3

Joint speaker diarisation and tracking in switching state-space model

2021-09-23 · Jeremy H. M. Wong, Yifan Gong

Speakers may move around while diarisation is being performed. When a microphone array is used, the instantaneous locations of where the sounds originated from can be estimated, and previous investigations have shown tha…

Advancing the dimensionality reduction of speaker embeddings for speaker diarisation: disentangling noise and informing speech activity

2021-10-07 · You Jin Kim, Hee-Soo Heo, Jee-weon Jung, Youngki Kwon 외

The objective of this work is to train noise-robust speaker embeddings adapted for speaker diarisation. Speaker embeddings play a crucial role in the performance of diarisation systems, but they often capture spurious in…

Dimensionality Reduction

Multi-scale speaker embedding-based graph attention networks for speaker diarisation

2021-10-07 · Youngki Kwon, Hee-Soo Heo, Jee-weon Jung, You Jin Kim 외

The objective of this work is effective speaker diarisation using multi-scale speaker embeddings. Typically, there is a trade-off between the ability to recognise short speaker segments and the discriminative power of th…

Graph Attention

Diarisation using location tracking with agglomerative clustering

2021-09-22 · Jeremy H. M. Wong, Igor Abramovski, Xiong Xiao, Yifan Gong

Previous works have shown that spatial location information can be complementary to speaker embeddings for a speaker diarisation task. However, the models used often assume that speakers are fairly stationary throughout …

Clustering