Multi-scale Speaker Embedding-based Graph Attention Networks For Speaker Diarisation

Abstract

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 the embedding, according to the segment length used for embedding extraction. To this end, recent works have proposed the use of multi-scale embeddings where segments with varying lengths are used. However, the scores are combined using a weighted summation scheme where the weights are fixed after the training phase, whereas the importance of segment lengths can differ with in a single session. To address this issue, we present three key contributions in this paper: (1) we propose graph attention networks for multi-scale speaker diarisation; (2) we design scale indicators to utilise scale information of each embedding; (3) we adapt the attention-based aggregation to utilise a pre-computed affinity matrix from multi-scale embeddings. We demonstrate the effectiveness of our

Stats

• citations12
• S2 citations—
• github stars0
• HF likes0
• heat score8.35
• arxiv keykwon2021multi

Related papers

• Multi-scale Speaker Diarization With Neural Affinity Score Fusion (2020)6.77
• Spectral Clustering-aware Learning Of Embeddings For Speaker Diarisation (2022)2.26
• Speaker Diarisation Using 2D Self-attentive Combination Of Embeddings (2019)9.92
• Leveraging Speaker Embeddings In End-to-end Neural Diarization For Two-speaker Scenarios (2024)0.00
• Speaker Diarization Using Deep Recurrent Convolutional Neural Networks For Speaker Embeddings (2017)9.41
• Improved Large-margin Softmax Loss For Speaker Diarisation (2019)6.34
• Graph Attention Networks For Speaker Verification (2020)9.23
• Advancing The Dimensionality Reduction Of Speaker Embeddings For Speaker Diarisation: Disentangling Noise And Informing Speech Activity (2021)2.26